Deblur Ground Truth — detail-chart, Sharp
The sharp reference for the detail-chart deblur set. Each blurred clip in this group applies a documented kernel to these exact pixels, so the deconvolution problem has a known answer — including which detail was destroyed outright and therefore cannot be recovered, only invented.
Browser-playable test video · 2 seconds
Specifications
- Resolution
- 640x360
- Fps
- 24
- Blur
- none
- Role
- ground truth
- Crf
- 14
- Base Plate
- detail-chart
Testing contract
Reference control- Scenario
- Use this clip as the reference term when scoring deblurring output produced from any degraded input in this group.
- Expected result
- The clip carries no blur, 640x360 at 24 fps. It is the detail-chart base plate at 640x360, 24 fps, encoded at CRF 14 so that codec artefacts sit well below the effect being measured. Every input in this group names this file in its own specs, so a score computed against anything else is not comparable with the rest of the suite.
What is a .mp4 file?
MP4 (MPEG-4 Part 14) is the dominant container for digital video, holding video, audio, subtitle, and metadata tracks in a tree of typed boxes. `ftyp` declares the brand, `moov` carries the sample tables that make seeking possible, and `mdat` holds the media; when an encoder writes `moov` last, playback cannot begin until the file has fully downloaded, which a faststart remux fixes. It derives from Apple's QuickTime format, generalized by ISO into the ISOBMFF base that MOV, 3GP, and HEIF share.
How to use this file
Use an example MP4 to test box parsing and track detection, seeking, range-request streaming, and transcode or thumbnail pipelines: verifying that a file with a trailing `moov` box is still handled, and that codec support is checked per track rather than inferred from the extension.
How to use this file for testing
“Deblur Ground Truth — detail-chart, Sharp” is a deterministic Novus Examples fixture for Video deblur, Video QA. Motion-blurred and defocused clips produced from a sharp source with a recorded kernel, so deblurring output can be measured against the original rather than compared to another blurred frame.
Documented properties for this file: ground truth · 24 fps. Compare results against paired or grouped companions on this page when present (clean↔damaged, searchable↔scanned, or format twins) so scores stay reproducible across runs.
Download the file once, keep the path stable in CI or local scripts, and treat the spec table as the contract: dimensions, seeds, field lists, and roles are intentional. Corrupt or invalid samples are labelled as such, expect parsers to fail loudly rather than silently accept them.
Media fixtures are short and synthetic by design. Prefer waveform or transcript ground truth in the same group when measuring ASR, trim, upscale, or sync tools; do not assume broadcast-quality masters.
Code examples
<video controls preload="metadata" width="640" src="detail-chart-sharp.mp4"></video>Related files
- mp4Deblur Ground Truth — text-motion, SharpThe sharp reference for the text-motion deblur set. Each blurred clip in this group applies a documented kernel to these exact pixels, so the deconvolution problem has a known answer — including which detail was destroyed outright and therefore cannot be recovered, only invented.
- mp4Deblur Input — text-motion, Defocus blur, radius 5Defocus blur, radius 5 applied to the sharp text-motion plate with a Gaussian kernel — a defocused lens. The kernel is documented, so this supports both blind and non-blind deconvolution: give the algorithm the kernel, or make it estimate one and compare.
- mp4Deblur Input — text-motion, Horizontal motion blur, 21 pxHorizontal motion blur, 21 px applied to the sharp text-motion plate with a uniform horizontal box kernel — a linear camera pan during exposure. The kernel is documented, so this supports both blind and non-blind deconvolution: give the algorithm the kernel, or make it estimate one and compare.
- mp4Deblur Input — text-motion, Horizontal motion blur, 9 pxHorizontal motion blur, 9 px applied to the sharp text-motion plate with a uniform horizontal box kernel — a linear camera pan during exposure. The kernel is documented, so this supports both blind and non-blind deconvolution: give the algorithm the kernel, or make it estimate one and compare.
- mp4Interpolation Input — depth-layers, Motion-Blurred DecimationHalved frame rate where each output frame is the AVERAGE of the two it replaces, rather than one of them — what a long shutter angle actually produces. Substantially harder than clean decimation, because the interpolator must undo motion blur as well as invent the missing instants, and no input frame matches any ground-truth frame exactly.
- mp4Interpolation Input — orbit-solid, Motion-Blurred DecimationHalved frame rate where each output frame is the AVERAGE of the two it replaces, rather than one of them — what a long shutter angle actually produces. Substantially harder than clean decimation, because the interpolator must undo motion blur as well as invent the missing instants, and no input frame matches any ground-truth frame exactly.
Generated by generation/video_ai_suites.py. Free for any use, no attribution required, license.