Generated stills, clips and audio published in several encodings of identical content, so a media pipeline can be tested on format handling, quality loss and frame or sample extraction against a reference that is known rather than assumed.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-av-f3.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f3.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f3.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f3.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f3.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-av-f3.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-av-f4.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f4.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f4.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f4.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f4.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-av-f4.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-av-f5.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f5.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f5.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f5.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-f5.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-av-f5.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-av-m3.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m3.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m3.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m3.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m3.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-av-m3.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-av-m4.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m4.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m4.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m4.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m4.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-av-m4.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-av-m5.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m5.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m5.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m5.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m5.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-av-m5.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-av-m6.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m6.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m6.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m6.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-m6.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-av-m6.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-av-nb1.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-nb1.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-nb1.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-nb1.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-av-nb1.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-av-nb1.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-avatar-f1.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-f1.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-f1.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-f1.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-f1.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-avatar-f1.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-avatar-f2.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-f2.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-f2.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-f2.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-f2.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-avatar-f2.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-avatar-m1.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-m1.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-m1.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-m1.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-m1.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-avatar-m1.
A synthetic photographic plate of a head-and-shoulders portrait on a plain ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate a-avatar-m2.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-m2.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-m2.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-m2.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate a-avatar-m2.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate a-avatar-m2.
A synthetic photographic plate of wordless square cover artwork, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate c-album-abs.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-abs.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-abs.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-abs.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-abs.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate c-album-abs.
A synthetic photographic plate of wordless square cover artwork, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate c-album-moody.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-moody.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-moody.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-moody.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-moody.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate c-album-moody.
A synthetic photographic plate of wordless square cover artwork, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate c-album-retro.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-retro.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-retro.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-retro.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-album-retro.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate c-album-retro.
A synthetic photographic plate of wordless portrait cover artwork, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate c-book-hist.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-hist.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-hist.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-hist.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-hist.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate c-book-hist.
A synthetic photographic plate of wordless portrait cover artwork, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate c-book-nature.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-nature.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-nature.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-nature.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-nature.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate c-book-nature.
A synthetic photographic plate of wordless portrait cover artwork, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate c-book-thrill.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-thrill.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-thrill.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-thrill.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate c-book-thrill.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate c-book-thrill.
A synthetic photographic plate of a photographic scene, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate d-clipboard.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-clipboard.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-clipboard.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-clipboard.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-clipboard.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate d-clipboard.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate d-invoice.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-invoice.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-invoice.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-invoice.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-invoice.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate d-invoice.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate d-ledger.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-ledger.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-ledger.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-ledger.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-ledger.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate d-ledger.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate d-menu.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-menu.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-menu.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-menu.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-menu.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate d-menu.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate d-receipts.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-receipts.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-receipts.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-receipts.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate d-receipts.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate d-receipts.
A synthetic photographic plate of a plated dish or food close-up, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate f-bread-rustic.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-bread-rustic.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-bread-rustic.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-bread-rustic.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-bread-rustic.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate f-bread-rustic.
A synthetic photographic plate of a plated dish or food close-up, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate f-coffee-pour.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-coffee-pour.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-coffee-pour.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-coffee-pour.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-coffee-pour.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate f-coffee-pour.
A synthetic photographic plate of a plated dish or food close-up, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate f-plate-pasta.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-plate-pasta.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-plate-pasta.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-plate-pasta.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-plate-pasta.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate f-plate-pasta.
A synthetic photographic plate of a plated dish or food close-up, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate f-plate-salad.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-plate-salad.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-plate-salad.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-plate-salad.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate f-plate-salad.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate f-plate-salad.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-char-knight.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-knight.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-knight.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-knight.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-knight.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-char-knight.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-char-mage.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-mage.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-mage.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-mage.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-mage.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-char-mage.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-char-scifi.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-scifi.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-scifi.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-scifi.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-scifi.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-char-scifi.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-dungeon.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-dungeon.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-dungeon.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-dungeon.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-dungeon.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-dungeon.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-fantasy-keep.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-fantasy-keep.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-fantasy-keep.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-fantasy-keep.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-fantasy-keep.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-fantasy-keep.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-isometric.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-isometric.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-isometric.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-isometric.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-isometric.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-isometric.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-lowpoly-isle.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-lowpoly-isle.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-lowpoly-isle.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-lowpoly-isle.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-lowpoly-isle.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-lowpoly-isle.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-pixel-scene.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-pixel-scene.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-pixel-scene.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-pixel-scene.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-pixel-scene.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-pixel-scene.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-platformer.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-platformer.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-platformer.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-platformer.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-platformer.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-platformer.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-racing-track.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-racing-track.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-racing-track.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-racing-track.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-racing-track.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-racing-track.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-scifi-corr.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-scifi-corr.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-scifi-corr.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-scifi-corr.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-scifi-corr.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-scifi-corr.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-voxel-city.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-voxel-city.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-voxel-city.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-voxel-city.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-voxel-city.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-voxel-city.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate invoice-desk.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate invoice-desk.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate invoice-desk.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate invoice-desk.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate invoice-desk.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate invoice-desk.
A synthetic photographic plate of a landscape or architectural scene, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate l-bridge.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-bridge.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-bridge.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-bridge.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-bridge.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate l-bridge.
A synthetic photographic plate of a landscape or architectural scene, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate l-city-sky.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-city-sky.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-city-sky.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-city-sky.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-city-sky.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate l-city-sky.
A synthetic photographic plate of a landscape or architectural scene, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate l-coast.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-coast.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-coast.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-coast.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-coast.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate l-coast.
A synthetic photographic plate of a landscape or architectural scene, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate l-forest-path.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-forest-path.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-forest-path.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-forest-path.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-forest-path.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate l-forest-path.
A synthetic photographic plate of a landscape or architectural scene, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate l-interior-mod.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-interior-mod.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-interior-mod.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-interior-mod.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-interior-mod.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate l-interior-mod.
A synthetic photographic plate of a landscape or architectural scene, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate l-mountain.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-mountain.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-mountain.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-mountain.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-mountain.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate l-mountain.
A synthetic photographic plate of a landscape or architectural scene, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate l-stairwell.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-stairwell.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-stairwell.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-stairwell.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-stairwell.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate l-stairwell.
A synthetic photographic plate of a landscape or architectural scene, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate l-street-eu.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-street-eu.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-street-eu.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-street-eu.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-street-eu.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate l-street-eu.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate ledger-book.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate ledger-book.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate ledger-book.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate ledger-book.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate ledger-book.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate ledger-book.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate meeting-table.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate meeting-table.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate meeting-table.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate meeting-table.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate meeting-table.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate meeting-table.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate menu-table.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate menu-table.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate menu-table.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate menu-table.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate menu-table.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate menu-table.
A synthetic photographic plate of an animal in a natural setting, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate n-birds-feed.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-birds-feed.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-birds-feed.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-birds-feed.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-birds-feed.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate n-birds-feed.
A synthetic photographic plate of an animal in a natural setting, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate n-cat-window.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-cat-window.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-cat-window.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-cat-window.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-cat-window.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate n-cat-window.
A synthetic photographic plate of an animal in a natural setting, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate n-dog-park.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-dog-park.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-dog-park.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-dog-park.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-dog-park.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate n-dog-park.
A synthetic photographic plate of an animal in a natural setting, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate n-fish-tank.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-fish-tank.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-fish-tank.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-fish-tank.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-fish-tank.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate n-fish-tank.
A synthetic photographic plate of an animal in a natural setting, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate n-horse-field.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-horse-field.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-horse-field.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-horse-field.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-horse-field.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate n-horse-field.
A synthetic photographic plate of an animal in a natural setting, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate n-sheep-hill.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-sheep-hill.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-sheep-hill.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-sheep-hill.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate n-sheep-hill.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate n-sheep-hill.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate office-desk.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate office-desk.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate office-desk.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate office-desk.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate office-desk.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate office-desk.
A synthetic photographic plate of an independent business owner, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate owner-cafe.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-cafe.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-cafe.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-cafe.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-cafe.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate owner-cafe.
A synthetic photographic plate of an independent business owner, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate owner-market.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-market.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-market.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-market.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-market.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate owner-market.
A synthetic photographic plate of an independent business owner, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate owner-restaurant.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-restaurant.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-restaurant.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-restaurant.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-restaurant.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate owner-restaurant.
A synthetic photographic plate of an independent business owner, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate owner-salon.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-salon.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-salon.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-salon.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-salon.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate owner-salon.
A synthetic photographic plate of an independent business owner, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate owner-shop.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-shop.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-shop.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-shop.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-shop.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate owner-shop.
A synthetic photographic plate of an independent business owner, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate owner-trades.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-trades.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-trades.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-trades.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate owner-trades.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate owner-trades.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-accountant.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-accountant.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-accountant.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-accountant.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-accountant.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-accountant.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-baker-young.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-baker-young.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-baker-young.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-baker-young.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-baker-young.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-baker-young.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-barista-deaf.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-barista-deaf.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-barista-deaf.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-barista-deaf.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-barista-deaf.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-barista-deaf.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-butcher-mid.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-butcher-mid.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-butcher-mid.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-butcher-mid.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-butcher-mid.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-butcher-mid.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-chef-wheel.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-chef-wheel.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-chef-wheel.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-chef-wheel.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-chef-wheel.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-chef-wheel.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-cleaner-eve.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-cleaner-eve.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-cleaner-eve.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-cleaner-eve.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-cleaner-eve.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-cleaner-eve.
A synthetic photographic plate of a person at work, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-desk-chair.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-desk-chair.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-desk-chair.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-desk-chair.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-desk-chair.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-desk-chair.
A synthetic photographic plate of a person at work, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-driver-eve.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-driver-eve.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-driver-eve.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-driver-eve.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-driver-eve.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-driver-eve.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-farmer-field.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-farmer-field.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-farmer-field.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-farmer-field.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-farmer-field.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-farmer-field.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-florist-sen.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-florist-sen.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-florist-sen.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-florist-sen.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-florist-sen.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-florist-sen.
A synthetic photographic plate of a person at work, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-kitchen-chef.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-kitchen-chef.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-kitchen-chef.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-kitchen-chef.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-kitchen-chef.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-kitchen-chef.
A synthetic photographic plate of a person at work, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-market-sen.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-market-sen.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-market-sen.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-market-sen.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-market-sen.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-market-sen.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-mechanic-w.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-mechanic-w.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-mechanic-w.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-mechanic-w.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-mechanic-w.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-mechanic-w.
A synthetic photographic plate of a person at work, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-meeting-mix.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-meeting-mix.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-meeting-mix.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-meeting-mix.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-meeting-mix.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-meeting-mix.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-nurse-clinic.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-nurse-clinic.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-nurse-clinic.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-nurse-clinic.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-nurse-clinic.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-nurse-clinic.
A synthetic photographic plate of a person at work, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-salon-mid.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-salon-mid.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-salon-mid.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-salon-mid.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-salon-mid.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-salon-mid.
A synthetic photographic plate of a person at work, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-shop-plus.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-shop-plus.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-shop-plus.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-shop-plus.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-shop-plus.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-shop-plus.
A synthetic photographic plate of a person at work, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-stick-cafe.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-stick-cafe.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-stick-cafe.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-stick-cafe.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-stick-cafe.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-stick-cafe.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-tailor-mid.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-tailor-mid.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-tailor-mid.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-tailor-mid.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-tailor-mid.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-tailor-mid.
A synthetic photographic plate of a person at work, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-teacher-cls.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-teacher-cls.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-teacher-cls.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-teacher-cls.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-teacher-cls.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-teacher-cls.
A synthetic photographic plate of a person at work, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-trades-w.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-trades-w.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-trades-w.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-trades-w.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-trades-w.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-trades-w.
A synthetic photographic plate of a person at work, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate p-ware-young.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-ware-young.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-ware-young.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-ware-young.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate p-ware-young.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate p-ware-young.
A synthetic photographic plate of a photographic scene, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate plate-food.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate plate-food.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate plate-food.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate plate-food.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate plate-food.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate plate-food.
A synthetic photographic plate of a single product on a plain studio ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate pr-backpack.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-backpack.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-backpack.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-backpack.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-backpack.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate pr-backpack.
A synthetic photographic plate of a single product on a plain studio ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate pr-bottle.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-bottle.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-bottle.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-bottle.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-bottle.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate pr-bottle.
A synthetic photographic plate of a single product on a plain studio ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate pr-headphone.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-headphone.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-headphone.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-headphone.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-headphone.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate pr-headphone.
A synthetic photographic plate of a single product on a plain studio ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate pr-laptop.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-laptop.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-laptop.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-laptop.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-laptop.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate pr-laptop.
A synthetic photographic plate of a single product on a plain studio ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate pr-plant-pot.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-plant-pot.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-plant-pot.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-plant-pot.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-plant-pot.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate pr-plant-pot.
A synthetic photographic plate of a single product on a plain studio ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate pr-shoe.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-shoe.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-shoe.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-shoe.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-shoe.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate pr-shoe.
A synthetic photographic plate of a single product on a plain studio ground, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate pr-watch.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-watch.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-watch.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-watch.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate pr-watch.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate pr-watch.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate receipt-counter.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate receipt-counter.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate receipt-counter.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate receipt-counter.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate receipt-counter.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate receipt-counter.
A synthetic photographic plate of an interior or storefront with no people, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-bakery.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-bakery.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-bakery.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-bakery.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-bakery.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-bakery.
A synthetic photographic plate of an interior or storefront with no people, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-cafe-empty.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-cafe-empty.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-cafe-empty.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-cafe-empty.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-cafe-empty.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-cafe-empty.
A synthetic photographic plate of an interior or storefront with no people, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-kitchen-clean.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-kitchen-clean.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-kitchen-clean.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-kitchen-clean.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-kitchen-clean.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-kitchen-clean.
A synthetic photographic plate of an interior or storefront with no people, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-market-stall.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-market-stall.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-market-stall.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-market-stall.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-market-stall.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-market-stall.
A synthetic photographic plate of an interior or storefront with no people, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-office-open.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-office-open.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-office-open.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-office-open.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-office-open.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-office-open.
A synthetic photographic plate of an interior or storefront with no people, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-office.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-office.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-office.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-office.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-office.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-office.
A synthetic photographic plate of an interior or storefront with no people, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-plate.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-plate.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-plate.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-plate.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-plate.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-plate.
A synthetic photographic plate of an interior or storefront with no people, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-shop-front.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-shop-front.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-shop-front.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-shop-front.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-shop-front.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-shop-front.
A synthetic photographic plate of an interior or storefront with no people, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-warehouse-a.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-warehouse-a.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-warehouse-a.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-warehouse-a.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-warehouse-a.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-warehouse-a.
A synthetic photographic plate of an interior or storefront with no people, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-workshop.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-workshop.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-workshop.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-workshop.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate s-workshop.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-workshop.
A synthetic photographic plate of a sporting activity, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate sp-climbing.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-climbing.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-climbing.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-climbing.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-climbing.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate sp-climbing.
A synthetic photographic plate of a sporting activity, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate sp-cyclists.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-cyclists.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-cyclists.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-cyclists.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-cyclists.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate sp-cyclists.
A synthetic photographic plate of a sporting activity, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate sp-football.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-football.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-football.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-football.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-football.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate sp-football.
A synthetic photographic plate of a sporting activity, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate sp-gym.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-gym.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-gym.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-gym.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-gym.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate sp-gym.
A synthetic photographic plate of a sporting activity, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate sp-runner.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-runner.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-runner.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-runner.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-runner.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate sp-runner.
A synthetic photographic plate of a sporting activity, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate sp-swimmer.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-swimmer.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-swimmer.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-swimmer.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate sp-swimmer.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate sp-swimmer.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate storefront.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate storefront.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate storefront.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate storefront.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate storefront.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate storefront.
A synthetic photographic plate of an out-of-focus light field, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-bokeh-warm.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-bokeh-warm.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-bokeh-warm.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-bokeh-warm.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-bokeh-warm.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-bokeh-warm.
A synthetic photographic plate of a smooth abstract gradient, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-grad-cool.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-cool.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-cool.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-cool.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-cool.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-grad-cool.
A synthetic photographic plate of a smooth abstract gradient, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-grad-mono2.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-mono2.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-mono2.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-mono2.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-mono2.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-grad-mono2.
A synthetic photographic plate of a smooth abstract gradient, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-grad-mono.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-mono.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-mono.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-mono.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-mono.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-grad-mono.
A synthetic photographic plate of a smooth abstract gradient, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-grad-warm.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-warm.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-warm.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-warm.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-grad-warm.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-grad-warm.
A synthetic photographic plate of a flowing mesh gradient, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-mesh-grad.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-mesh-grad.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-mesh-grad.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-mesh-grad.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-mesh-grad.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-mesh-grad.
A synthetic photographic plate of a soft low-detail background plate, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-ph-dark1.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-dark1.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-dark1.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-dark1.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-dark1.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-ph-dark1.
A synthetic photographic plate of a soft low-detail background plate, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-ph-dark2.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-dark2.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-dark2.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-dark2.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-dark2.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-ph-dark2.
A synthetic photographic plate of a soft low-detail background plate, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-ph-mesh2.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-mesh2.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-mesh2.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-mesh2.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-mesh2.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-ph-mesh2.
A synthetic photographic plate of a soft low-detail background plate, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-ph-soft1.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft1.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft1.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft1.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft1.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-ph-soft1.
A synthetic photographic plate of a soft low-detail background plate, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-ph-soft2.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft2.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft2.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft2.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft2.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-ph-soft2.
A synthetic photographic plate of a soft low-detail background plate, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-ph-soft3.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft3.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft3.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft3.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-ph-soft3.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-ph-soft3.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-brick.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-brick.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-brick.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-brick.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-brick.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-brick.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-concrete.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-concrete.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-concrete.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-concrete.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-concrete.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-concrete.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-denim.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-denim.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-denim.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-denim.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-denim.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-denim.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-leather.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-leather.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-leather.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-leather.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-leather.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-leather.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-linen.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-linen.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-linen.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-linen.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-linen.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-linen.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-marble.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-marble.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-marble.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-marble.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-marble.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-marble.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-paper2.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-paper2.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-paper2.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-paper2.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-paper2.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-paper2.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-paper.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-paper.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-paper.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-paper.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-paper.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-paper.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-rust.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-rust.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-rust.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-rust.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-rust.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-rust.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-sand.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-sand.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-sand.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-sand.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-sand.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-sand.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-slate.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-slate.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-slate.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-slate.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-slate.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-slate.
A synthetic photographic plate of a flat surface texture under even light, 1024x683, lossless PNG. This is the reference every lossy variant in this group is derived from Plate t-tex-wood.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-wood.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-wood.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-wood.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate t-tex-wood.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate t-tex-wood.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-bike-city.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-bike-city.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-bike-city.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-bike-city.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-bike-city.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-bike-city.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-boat-harbour.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-boat-harbour.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-boat-harbour.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-boat-harbour.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-boat-harbour.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-boat-harbour.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-bus-city.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-bus-city.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-bus-city.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-bus-city.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-bus-city.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-bus-city.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-car-classic.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-classic.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-classic.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-classic.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-classic.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-car-classic.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-car-ev.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-ev.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-ev.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-ev.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-ev.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-car-ev.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-car-night.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-night.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-night.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-night.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-night.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-car-night.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-car-sedan.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-sedan.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-sedan.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-sedan.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-car-sedan.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-car-sedan.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-forklift.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-forklift.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-forklift.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-forklift.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-forklift.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-forklift.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-moto-sport.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-moto-sport.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-moto-sport.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-moto-sport.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-moto-sport.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-moto-sport.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-pickup-mud.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-pickup-mud.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-pickup-mud.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-pickup-mud.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-pickup-mud.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-pickup-mud.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-plane-gate.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-plane-gate.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-plane-gate.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-plane-gate.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-plane-gate.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-plane-gate.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-scooter.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-scooter.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-scooter.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-scooter.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-scooter.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-scooter.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-tractor.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-tractor.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-tractor.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-tractor.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-tractor.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-tractor.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-train-plat.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-train-plat.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-train-plat.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-train-plat.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-train-plat.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-train-plat.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-truck-artic.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-truck-artic.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-truck-artic.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-truck-artic.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-truck-artic.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-truck-artic.
A synthetic photographic plate of a vehicle in context, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate v-van-delivery.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-van-delivery.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-van-delivery.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-van-delivery.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate v-van-delivery.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate v-van-delivery.
A synthetic photographic plate of a photographic scene, 1024x701, lossless PNG. This is the reference every lossy variant in this group is derived from Plate warehouse-clip.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate warehouse-clip.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate warehouse-clip.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate warehouse-clip.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate warehouse-clip.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate warehouse-clip.
The same 512x512 photograph written as png 24bit. The lossless reference for this group; every lossy member is scored against it. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as png interlaced. Adam7 interlacing decodes in seven passes rather than one, which is a separate code path. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as png palette256. A palette PNG carries indices and a colour table, not RGB pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as png grayscale. Single channel, so a reader assuming three will read past the end of a row. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as jpeg q92. Baseline JPEG at quality 92. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as jpeg q60. Baseline JPEG at quality 60. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as jpeg progressive. Progressive scan order, which a naive reader renders as a blurry first pass or not at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as webp lossy. Lossy WebP. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as webp lossless. Lossless WebP, a different bitstream from the lossy one. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as avif lossy. AV1 still image: modern, small, and unsupported by a surprising amount of tooling. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as tiff uncompressed. Raw strips, the simplest TIFF and the largest. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as tiff lzw. LZW, the TIFF compression most readers assume. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as tiff deflate. Deflate inside TIFF. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as tiff jpeg. A lossy JPEG stream inside a TIFF container, which breaks the assumption that TIFF is lossless. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as tiff 16bit gray. 16 bits per sample: a reader that truncates to 8 loses half the range silently. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as bmp 24bit. BMP stores rows bottom-up, so a reader that ignores that returns the image flipped. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as gif 256. GIF cannot hold more than 256 colours, so this is quantised by the format itself. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as tga rle. Run-length encoded Targa. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as ppm binary. Netpbm binary: a tiny header then raw bytes, with no compression at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as pgm binary. Greyscale Netpbm. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as jp2 lossless. Wavelet coding, reversible mode; shares an extension family with the lossy variant below. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as jp2 lossy. Irreversible wavelet coding. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as ico multisize. One file holding four resolutions; a reader that takes the first gets 16 pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x512 photograph written as heic. What an iPhone produces by default, and what a lot of pipelines still cannot read. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate a-av-f3.
The same 512x350 photograph written as png 24bit. The lossless reference for this group; every lossy member is scored against it. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as png interlaced. Adam7 interlacing decodes in seven passes rather than one, which is a separate code path. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as png palette256. A palette PNG carries indices and a colour table, not RGB pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as png grayscale. Single channel, so a reader assuming three will read past the end of a row. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as jpeg q92. Baseline JPEG at quality 92. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as jpeg q60. Baseline JPEG at quality 60. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as jpeg progressive. Progressive scan order, which a naive reader renders as a blurry first pass or not at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as webp lossy. Lossy WebP. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as webp lossless. Lossless WebP, a different bitstream from the lossy one. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as avif lossy. AV1 still image: modern, small, and unsupported by a surprising amount of tooling. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as tiff uncompressed. Raw strips, the simplest TIFF and the largest. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as tiff lzw. LZW, the TIFF compression most readers assume. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as tiff deflate. Deflate inside TIFF. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as tiff jpeg. A lossy JPEG stream inside a TIFF container, which breaks the assumption that TIFF is lossless. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as tiff 16bit gray. 16 bits per sample: a reader that truncates to 8 loses half the range silently. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as bmp 24bit. BMP stores rows bottom-up, so a reader that ignores that returns the image flipped. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as gif 256. GIF cannot hold more than 256 colours, so this is quantised by the format itself. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as tga rle. Run-length encoded Targa. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as ppm binary. Netpbm binary: a tiny header then raw bytes, with no compression at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as pgm binary. Greyscale Netpbm. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as jp2 lossless. Wavelet coding, reversible mode; shares an extension family with the lossy variant below. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as jp2 lossy. Irreversible wavelet coding. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as ico multisize. One file holding four resolutions; a reader that takes the first gets 16 pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x350 photograph written as heic. What an iPhone produces by default, and what a lot of pipelines still cannot read. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate p-market-sen.
The same 512x512 photograph written as png 24bit. The lossless reference for this group; every lossy member is scored against it. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as png interlaced. Adam7 interlacing decodes in seven passes rather than one, which is a separate code path. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as png palette256. A palette PNG carries indices and a colour table, not RGB pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as png grayscale. Single channel, so a reader assuming three will read past the end of a row. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as jpeg q92. Baseline JPEG at quality 92. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as jpeg q60. Baseline JPEG at quality 60. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as jpeg progressive. Progressive scan order, which a naive reader renders as a blurry first pass or not at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as webp lossy. Lossy WebP. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as webp lossless. Lossless WebP, a different bitstream from the lossy one. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as avif lossy. AV1 still image: modern, small, and unsupported by a surprising amount of tooling. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as tiff uncompressed. Raw strips, the simplest TIFF and the largest. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as tiff lzw. LZW, the TIFF compression most readers assume. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as tiff deflate. Deflate inside TIFF. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as tiff jpeg. A lossy JPEG stream inside a TIFF container, which breaks the assumption that TIFF is lossless. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as tiff 16bit gray. 16 bits per sample: a reader that truncates to 8 loses half the range silently. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as bmp 24bit. BMP stores rows bottom-up, so a reader that ignores that returns the image flipped. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as gif 256. GIF cannot hold more than 256 colours, so this is quantised by the format itself. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as tga rle. Run-length encoded Targa. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as ppm binary. Netpbm binary: a tiny header then raw bytes, with no compression at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as pgm binary. Greyscale Netpbm. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as jp2 lossless. Wavelet coding, reversible mode; shares an extension family with the lossy variant below. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as jp2 lossy. Irreversible wavelet coding. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as ico multisize. One file holding four resolutions; a reader that takes the first gets 16 pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as heic. What an iPhone produces by default, and what a lot of pipelines still cannot read. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate v-car-sedan.
The same 512x512 photograph written as png 24bit. The lossless reference for this group; every lossy member is scored against it. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as png interlaced. Adam7 interlacing decodes in seven passes rather than one, which is a separate code path. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as png palette256. A palette PNG carries indices and a colour table, not RGB pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as png grayscale. Single channel, so a reader assuming three will read past the end of a row. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as jpeg q92. Baseline JPEG at quality 92. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as jpeg q60. Baseline JPEG at quality 60. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as jpeg progressive. Progressive scan order, which a naive reader renders as a blurry first pass or not at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as webp lossy. Lossy WebP. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as webp lossless. Lossless WebP, a different bitstream from the lossy one. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as avif lossy. AV1 still image: modern, small, and unsupported by a surprising amount of tooling. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as tiff uncompressed. Raw strips, the simplest TIFF and the largest. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as tiff lzw. LZW, the TIFF compression most readers assume. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as tiff deflate. Deflate inside TIFF. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as tiff jpeg. A lossy JPEG stream inside a TIFF container, which breaks the assumption that TIFF is lossless. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as tiff 16bit gray. 16 bits per sample: a reader that truncates to 8 loses half the range silently. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as bmp 24bit. BMP stores rows bottom-up, so a reader that ignores that returns the image flipped. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as gif 256. GIF cannot hold more than 256 colours, so this is quantised by the format itself. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as tga rle. Run-length encoded Targa. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as ppm binary. Netpbm binary: a tiny header then raw bytes, with no compression at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as pgm binary. Greyscale Netpbm. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as jp2 lossless. Wavelet coding, reversible mode; shares an extension family with the lossy variant below. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as jp2 lossy. Irreversible wavelet coding. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as ico multisize. One file holding four resolutions; a reader that takes the first gets 16 pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x512 photograph written as heic. What an iPhone produces by default, and what a lot of pipelines still cannot read. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate f-plate-pasta.
The same 512x341 photograph written as png 24bit. The lossless reference for this group; every lossy member is scored against it. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as png interlaced. Adam7 interlacing decodes in seven passes rather than one, which is a separate code path. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as png palette256. A palette PNG carries indices and a colour table, not RGB pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as png grayscale. Single channel, so a reader assuming three will read past the end of a row. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as jpeg q92. Baseline JPEG at quality 92. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as jpeg q60. Baseline JPEG at quality 60. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as jpeg progressive. Progressive scan order, which a naive reader renders as a blurry first pass or not at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as webp lossy. Lossy WebP. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as webp lossless. Lossless WebP, a different bitstream from the lossy one. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as avif lossy. AV1 still image: modern, small, and unsupported by a surprising amount of tooling. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as tiff uncompressed. Raw strips, the simplest TIFF and the largest. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as tiff lzw. LZW, the TIFF compression most readers assume. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as tiff deflate. Deflate inside TIFF. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as tiff jpeg. A lossy JPEG stream inside a TIFF container, which breaks the assumption that TIFF is lossless. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as tiff 16bit gray. 16 bits per sample: a reader that truncates to 8 loses half the range silently. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as bmp 24bit. BMP stores rows bottom-up, so a reader that ignores that returns the image flipped. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as gif 256. GIF cannot hold more than 256 colours, so this is quantised by the format itself. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as tga rle. Run-length encoded Targa. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as ppm binary. Netpbm binary: a tiny header then raw bytes, with no compression at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as pgm binary. Greyscale Netpbm. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as jp2 lossless. Wavelet coding, reversible mode; shares an extension family with the lossy variant below. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as jp2 lossy. Irreversible wavelet coding. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as ico multisize. One file holding four resolutions; a reader that takes the first gets 16 pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as heic. What an iPhone produces by default, and what a lot of pipelines still cannot read. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-tex-brick.
The same 512x341 photograph written as png 24bit. The lossless reference for this group; every lossy member is scored against it. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as png interlaced. Adam7 interlacing decodes in seven passes rather than one, which is a separate code path. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as png palette256. A palette PNG carries indices and a colour table, not RGB pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as png grayscale. Single channel, so a reader assuming three will read past the end of a row. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as jpeg q92. Baseline JPEG at quality 92. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as jpeg q60. Baseline JPEG at quality 60. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as jpeg progressive. Progressive scan order, which a naive reader renders as a blurry first pass or not at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as webp lossy. Lossy WebP. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as webp lossless. Lossless WebP, a different bitstream from the lossy one. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as avif lossy. AV1 still image: modern, small, and unsupported by a surprising amount of tooling. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as tiff uncompressed. Raw strips, the simplest TIFF and the largest. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as tiff lzw. LZW, the TIFF compression most readers assume. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as tiff deflate. Deflate inside TIFF. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as tiff jpeg. A lossy JPEG stream inside a TIFF container, which breaks the assumption that TIFF is lossless. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as tiff 16bit gray. 16 bits per sample: a reader that truncates to 8 loses half the range silently. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as bmp 24bit. BMP stores rows bottom-up, so a reader that ignores that returns the image flipped. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as gif 256. GIF cannot hold more than 256 colours, so this is quantised by the format itself. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as tga rle. Run-length encoded Targa. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as ppm binary. Netpbm binary: a tiny header then raw bytes, with no compression at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as pgm binary. Greyscale Netpbm. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as jp2 lossless. Wavelet coding, reversible mode; shares an extension family with the lossy variant below. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as jp2 lossy. Irreversible wavelet coding. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as ico multisize. One file holding four resolutions; a reader that takes the first gets 16 pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x341 photograph written as heic. What an iPhone produces by default, and what a lot of pipelines still cannot read. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate t-grad-cool.
The same 512x512 photograph written as png 24bit. The lossless reference for this group; every lossy member is scored against it. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as png interlaced. Adam7 interlacing decodes in seven passes rather than one, which is a separate code path. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as png palette256. A palette PNG carries indices and a colour table, not RGB pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as png grayscale. Single channel, so a reader assuming three will read past the end of a row. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as jpeg q92. Baseline JPEG at quality 92. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as jpeg q60. Baseline JPEG at quality 60. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as jpeg progressive. Progressive scan order, which a naive reader renders as a blurry first pass or not at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as webp lossy. Lossy WebP. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as webp lossless. Lossless WebP, a different bitstream from the lossy one. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as avif lossy. AV1 still image: modern, small, and unsupported by a surprising amount of tooling. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as tiff uncompressed. Raw strips, the simplest TIFF and the largest. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as tiff lzw. LZW, the TIFF compression most readers assume. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as tiff deflate. Deflate inside TIFF. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as tiff jpeg. A lossy JPEG stream inside a TIFF container, which breaks the assumption that TIFF is lossless. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as tiff 16bit gray. 16 bits per sample: a reader that truncates to 8 loses half the range silently. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as bmp 24bit. BMP stores rows bottom-up, so a reader that ignores that returns the image flipped. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as gif 256. GIF cannot hold more than 256 colours, so this is quantised by the format itself. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as tga rle. Run-length encoded Targa. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as ppm binary. Netpbm binary: a tiny header then raw bytes, with no compression at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as pgm binary. Greyscale Netpbm. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as jp2 lossless. Wavelet coding, reversible mode; shares an extension family with the lossy variant below. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as jp2 lossy. Irreversible wavelet coding. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as ico multisize. One file holding four resolutions; a reader that takes the first gets 16 pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as heic. What an iPhone produces by default, and what a lot of pipelines still cannot read. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate g-fantasy-keep.
The same 512x512 photograph written as png 24bit. The lossless reference for this group; every lossy member is scored against it. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as png interlaced. Adam7 interlacing decodes in seven passes rather than one, which is a separate code path. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as png palette256. A palette PNG carries indices and a colour table, not RGB pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as png grayscale. Single channel, so a reader assuming three will read past the end of a row. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as jpeg q92. Baseline JPEG at quality 92. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as jpeg q60. Baseline JPEG at quality 60. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as jpeg progressive. Progressive scan order, which a naive reader renders as a blurry first pass or not at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as webp lossy. Lossy WebP. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as webp lossless. Lossless WebP, a different bitstream from the lossy one. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as avif lossy. AV1 still image: modern, small, and unsupported by a surprising amount of tooling. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as tiff uncompressed. Raw strips, the simplest TIFF and the largest. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as tiff lzw. LZW, the TIFF compression most readers assume. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as tiff deflate. Deflate inside TIFF. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as tiff jpeg. A lossy JPEG stream inside a TIFF container, which breaks the assumption that TIFF is lossless. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as tiff 16bit gray. 16 bits per sample: a reader that truncates to 8 loses half the range silently. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as bmp 24bit. BMP stores rows bottom-up, so a reader that ignores that returns the image flipped. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as gif 256. GIF cannot hold more than 256 colours, so this is quantised by the format itself. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as tga rle. Run-length encoded Targa. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as ppm binary. Netpbm binary: a tiny header then raw bytes, with no compression at all. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as pgm binary. Greyscale Netpbm. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as jp2 lossless. Wavelet coding, reversible mode; shares an extension family with the lossy variant below. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as jp2 lossy. Irreversible wavelet coding. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as ico multisize. One file holding four resolutions; a reader that takes the first gets 16 pixels. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The same 512x512 photograph written as heic. What an iPhone produces by default, and what a lot of pipelines still cannot read. Every member of this group is identical pixels, so a decoder returning different dimensions or a different pixel count has lost something rather than simply produced a different file; the 24-bit PNG in this group is lossless and is the reference the lossy members are measured against Source plate pr-shoe.
The scrub-preview sheet for the film in this group: 24 tiles in a 6x4 grid, one sampled per second, each 160x90. This is the form a player requests when a viewer drags the scrubber. A two-second clip yields two tiles and proves nothing about tiling; 24 seconds fills the grid.
The scrub-preview sheet for the film in this group: 24 tiles in a 6x4 grid, one sampled per second, each 160x90. This is the form a player requests when a viewer drags the scrubber. A two-second clip yields two tiles and proves nothing about tiling; 24 seconds fills the grid.
The scrub-preview sheet for the film in this group: 24 tiles in a 6x4 grid, one sampled per second, each 160x90. This is the form a player requests when a viewer drags the scrubber. A two-second clip yields two tiles and proves nothing about tiling; 24 seconds fills the grid.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-v-bike-city_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0586 (active). Substantial frame-to-frame change, the end of the range where naive scene detection starts firing. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-owner-cafe_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0175 (moderate). Clear movement without a scene change, which is the ordinary case for short footage. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-v-car-sedan_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0342 (moderate). Clear movement without a scene change, which is the ordinary case for short footage. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-n-cat-window_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0182 (moderate). Clear movement without a scene change, which is the ordinary case for short footage. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-l-coast_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0214 (moderate). Clear movement without a scene change, which is the ordinary case for short footage. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-n-dog-park_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0312 (moderate). Clear movement without a scene change, which is the ordinary case for short footage. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-l-forest-path_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0131 (subtle). Motion is deliberate but slight, closer to a living photograph than to action. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-g-fantasy-keep_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0051 (subtle). Motion is deliberate but slight, closer to a living photograph than to action. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-owner-cafe_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0261 (moderate). Clear movement without a scene change, which is the ordinary case for short footage. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-p-market-sen_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0563 (active). Substantial frame-to-frame change, the end of the range where naive scene detection starts firing. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-p-kitchen-chef_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0287 (moderate). Clear movement without a scene change, which is the ordinary case for short footage. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-l-mountain_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0070 (subtle). Motion is deliberate but slight, closer to a living photograph than to action. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-f-plate-pasta_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0163 (moderate). Clear movement without a scene change, which is the ordinary case for short footage. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-owner-restaurant_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0148 (subtle). Motion is deliberate but slight, closer to a living photograph than to action. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-sp-runner_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0508 (active). Substantial frame-to-frame change, the end of the range where naive scene detection starts firing. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-owner-salon_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0082 (subtle). Motion is deliberate but slight, closer to a living photograph than to action. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-owner-shop_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0107 (subtle). Motion is deliberate but slight, closer to a living photograph than to action. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-p-stick-cafe_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0517 (active). Substantial frame-to-frame change, the end of the range where naive scene detection starts firing. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.1 second 512x288 H.264 clip at 8 fps, 17 frames. Generated from a text prompt alone, kept as the low-resolution, non-standard-frame-rate case that decoder tests need and photographic clips do not provide. Measured mean inter-frame change 0.0174 (moderate). Clear movement without a scene change, which is the ordinary case for short footage. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-v-truck-artic_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0269 (moderate). Clear movement without a scene change, which is the ordinary case for short footage. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 2.0 second 640x480 H.264 clip at 24 fps, 49 frames. Animated from the still nss-warehouse-clip_00001_.png, so the first frame is a known image and frame extraction can be checked against it. Measured mean inter-frame change 0.0452 (active). Substantial frame-to-frame change, the end of the range where naive scene detection starts firing. Synthetic footage: two seconds at this size is a decoder and pipeline fixture rather than showcase material, hands degrade in later frames, and no text in shot is legible.
A 24 second 512x288 H.264 film at 24 fps, 576 frames, written with the moov atom first so it can be seeked before it has finished downloading. Twelve generated segments crossfaded into one continuous take. Across 575 transitions the mean inter-frame change is 0.0217 and the strongest single transition is 0.2597, with 0 above 0.3. A deliberate hard cut between two unrelated films measures 0.311 by the same method, so the worst join here sits 0.0513 below a real cut. At eleven times the length of any other clip in this library, it is the only footage here long enough to seek through, chapter, or scrub. Stylised rather than photographic: this is the 1.3B model at 512x288, the subject drifts over 24 seconds, and a dark rendering artefact recurs in a few frames. It is a fixture for duration, seeking and stitch measurement, not showcase footage.
The WebVTT index for the sprite sheet in this group: 24 cues, one per second, each naming a rectangle of the sheet with an xywh media fragment. The sheet and this index are each useless alone, which is why they are paired.
A 24 second 512x288 H.264 film at 24 fps, 576 frames, written with the moov atom first so it can be seeked before it has finished downloading. Twelve generated segments crossfaded into one continuous take. Across 575 transitions the mean inter-frame change is 0.0139 and the strongest single transition is 0.1614, with 0 above 0.3. A deliberate hard cut between two unrelated films measures 0.311 by the same method, so the worst join here sits 0.1496 below a real cut. At eleven times the length of any other clip in this library, it is the only footage here long enough to seek through, chapter, or scrub. Stylised rather than photographic: this is the 1.3B model at 512x288, the subject drifts over 24 seconds, and a dark rendering artefact recurs in a few frames. It is a fixture for duration, seeking and stitch measurement, not showcase footage.
The WebVTT index for the sprite sheet in this group: 24 cues, one per second, each naming a rectangle of the sheet with an xywh media fragment. The sheet and this index are each useless alone, which is why they are paired.
A 24 second 512x288 H.264 film at 24 fps, 576 frames, written with the moov atom first so it can be seeked before it has finished downloading. Twelve generated segments crossfaded into one continuous take. Across 575 transitions the mean inter-frame change is 0.0206 and the strongest single transition is 0.2395, with 0 above 0.3. A deliberate hard cut between two unrelated films measures 0.311 by the same method, so the worst join here sits 0.0715 below a real cut. At eleven times the length of any other clip in this library, it is the only footage here long enough to seek through, chapter, or scrub. Stylised rather than photographic: this is the 1.3B model at 512x288, the subject drifts over 24 seconds, and a dark rendering artefact recurs in a few frames. It is a fixture for duration, seeking and stitch measurement, not showcase footage.
The WebVTT index for the sprite sheet in this group: 24 cues, one per second, each naming a rectangle of the sheet with an xywh media fragment. The sheet and this index are each useless alone, which is why they are paired.
We use Google Analytics and show ads via Adsterra. Non-essential cookies and ad scripts run only after you allow the matching categories. See our cookie policy.
