Explore the test library

Search files, editable visual templates, and live browser targets from one registry-backed directory. Filtered query views stay crawlable for links but are deliberately noindex; the stable taxonomy pages below remain the canonical search surfaces.

402 results

Page 5 of 17; 24 results per page.

Show the canonical directory

Preview of DASH VOD — Manifest (Playable Package) — Actual file preview for DASH VOD — Manifest (Playable Package)

DASH VOD — Manifest (Playable Package)

A complete, playable MPEG-DASH manifest for the same 320x180 at 300 kbps, 480x270 at 700 kbps, 640x360 at 1400 kbps ladder as the HLS package, produced from the same encoder run — so the two can be compared directly as packaging rather than as content. Every segment it references exists in this group. Served inline as application/dash+xml with permissive CORS, so dash.js can load it cross-origin.

File: MPD · Vod Dash
Use case: Streaming manifestsVideo codecs+1· Conversion set

Preview of DASH VOD — Media Segment (chunk-stream0-00001.m4s) — Actual file preview for DASH VOD — Media Segment (chunk-stream0-00001.m4s)

DASH VOD — Media Segment (chunk-stream0-00001.m4s)

A one-second DASH media segment, addressed by the manifest's $Number$ template. The same underlying CMAF structure as the HLS segments in the sibling package — which is the whole point of CMAF, and something a fixture set should let you verify rather than take on trust.

File: M4S · Vod Dash
Use case: Streaming manifestsVideo codecs+1· Conversion set

Preview of DASH VOD — Media Segment (chunk-stream0-00002.m4s) — Actual file preview for DASH VOD — Media Segment (chunk-stream0-00002.m4s)

DASH VOD — Media Segment (chunk-stream0-00002.m4s)

A one-second DASH media segment, addressed by the manifest's $Number$ template. The same underlying CMAF structure as the HLS segments in the sibling package — which is the whole point of CMAF, and something a fixture set should let you verify rather than take on trust.

File: M4S · Vod Dash
Use case: Streaming manifestsVideo codecs+1· Conversion set

Preview of DASH VOD — Media Segment (chunk-stream1-00001.m4s) — Actual file preview for DASH VOD — Media Segment (chunk-stream1-00001.m4s)

DASH VOD — Media Segment (chunk-stream1-00001.m4s)

A one-second DASH media segment, addressed by the manifest's $Number$ template. The same underlying CMAF structure as the HLS segments in the sibling package — which is the whole point of CMAF, and something a fixture set should let you verify rather than take on trust.

File: M4S · Vod Dash
Use case: Streaming manifestsVideo codecs+1· Conversion set

Preview of DASH VOD — Media Segment (chunk-stream1-00002.m4s) — Actual file preview for DASH VOD — Media Segment (chunk-stream1-00002.m4s)

DASH VOD — Media Segment (chunk-stream1-00002.m4s)

A one-second DASH media segment, addressed by the manifest's $Number$ template. The same underlying CMAF structure as the HLS segments in the sibling package — which is the whole point of CMAF, and something a fixture set should let you verify rather than take on trust.

File: M4S · Vod Dash
Use case: Streaming manifestsVideo codecs+1· Conversion set

Preview of DASH VOD — Media Segment (chunk-stream2-00001.m4s) — Actual file preview for DASH VOD — Media Segment (chunk-stream2-00001.m4s)

DASH VOD — Media Segment (chunk-stream2-00001.m4s)

A one-second DASH media segment, addressed by the manifest's $Number$ template. The same underlying CMAF structure as the HLS segments in the sibling package — which is the whole point of CMAF, and something a fixture set should let you verify rather than take on trust.

File: M4S · Vod Dash
Use case: Streaming manifestsVideo codecs+1· Conversion set

Preview of DASH VOD — Media Segment (chunk-stream2-00002.m4s) — Actual file preview for DASH VOD — Media Segment (chunk-stream2-00002.m4s)

DASH VOD — Media Segment (chunk-stream2-00002.m4s)

A one-second DASH media segment, addressed by the manifest's $Number$ template. The same underlying CMAF structure as the HLS segments in the sibling package — which is the whole point of CMAF, and something a fixture set should let you verify rather than take on trust.

File: M4S · Vod Dash
Use case: Streaming manifestsVideo codecs+1· Conversion set

Preview of Deblur Ground Truth — detail-chart, Sharp — Actual file preview for Deblur Ground Truth — detail-chart, Sharp

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.

File: MP4 · Deblur · 640x360
Use case: Video deblurVideo QA· Conversion set

Preview of Deblur Ground Truth — text-motion, Sharp — Actual file preview for Deblur Ground Truth — text-motion, Sharp

Deblur Ground Truth — text-motion, Sharp

The 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.

File: MP4 · Deblur · 640x360
Use case: Video deblurVideo QA· Conversion set

Preview of Deblur Input — detail-chart, Defocus blur, radius 5 — Actual file preview for Deblur Input — detail-chart, Defocus blur, radius 5

Deblur Input — detail-chart, Defocus blur, radius 5

Defocus blur, radius 5 applied to the sharp detail-chart 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.

File: MP4 · Deblur · 640x360
Use case: Video deblurVideo QA· Conversion set

Preview of Deblur Input — detail-chart, Horizontal motion blur, 21 px — Actual file preview for Deblur Input — detail-chart, Horizontal motion blur, 21 px

Deblur Input — detail-chart, Horizontal motion blur, 21 px

Horizontal motion blur, 21 px applied to the sharp detail-chart 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.

File: MP4 · Deblur · 640x360
Use case: Video deblurVideo QA· Conversion set

Preview of Deblur Input — detail-chart, Horizontal motion blur, 9 px — Actual file preview for Deblur Input — detail-chart, Horizontal motion blur, 9 px

Deblur Input — detail-chart, Horizontal motion blur, 9 px

Horizontal motion blur, 9 px applied to the sharp detail-chart 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.

File: MP4 · Deblur · 640x360
Use case: Video deblurVideo QA· Conversion set

Preview of Deblur Input — text-motion, Defocus blur, radius 5 — Actual file preview for Deblur Input — text-motion, Defocus blur, radius 5

Deblur Input — text-motion, Defocus blur, radius 5

Defocus 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.

File: MP4 · Deblur · 640x360
Use case: Video deblurVideo QA· Conversion set

Preview of Deblur Input — text-motion, Horizontal motion blur, 21 px — Actual file preview for Deblur Input — text-motion, Horizontal motion blur, 21 px

Deblur Input — text-motion, Horizontal motion blur, 21 px

Horizontal 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.

File: MP4 · Deblur · 640x360
Use case: Video deblurVideo QA· Conversion set

Preview of Deblur Input — text-motion, Horizontal motion blur, 9 px — Actual file preview for Deblur Input — text-motion, Horizontal motion blur, 9 px

Deblur Input — text-motion, Horizontal motion blur, 9 px

Horizontal 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.

File: MP4 · Deblur · 640x360
Use case: Video deblurVideo QA· Conversion set

Preview of Denoise Ground Truth — detail-chart — Actual file preview for Denoise Ground Truth — detail-chart

Denoise Ground Truth — detail-chart

The clean reference for the detail-chart denoise set — no noise added, encoded at CRF 14. Every noisy clip in this group was produced from these exact pixels, so PSNR, SSIM and LPIPS against this file are meaningful rather than approximate.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Preview of Denoise Ground Truth — gradient-sky — Actual file preview for Denoise Ground Truth — gradient-sky

Denoise Ground Truth — gradient-sky

The clean reference for the gradient-sky denoise set — no noise added, encoded at CRF 14. Every noisy clip in this group was produced from these exact pixels, so PSNR, SSIM and LPIPS against this file are meaningful rather than approximate.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Preview of Denoise Ground Truth — pan-city — Actual file preview for Denoise Ground Truth — pan-city

Denoise Ground Truth — pan-city

The clean reference for the pan-city denoise set — no noise added, encoded at CRF 14. Every noisy clip in this group was produced from these exact pixels, so PSNR, SSIM and LPIPS against this file are meaningful rather than approximate.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Preview of Denoise Input — detail-chart, Gaussian σ=15 — Actual file preview for Denoise Input — detail-chart, Gaussian σ=15

Denoise Input — detail-chart, Gaussian σ=15

Gaussian σ=15 applied to the detail-chart base plate with seed 9017. Moderate Gaussian noise, roughly a mid-ISO handheld shot. The level most denoise benchmarks use. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 19, where the light noise could otherwise be confused with compression artefacts.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Preview of Denoise Input — detail-chart, Gaussian σ=30 — Actual file preview for Denoise Input — detail-chart, Gaussian σ=30

Denoise Input — detail-chart, Gaussian σ=30

Gaussian σ=30 applied to the detail-chart base plate with seed 9034. Heavy Gaussian noise where fine detail and noise overlap in amplitude, so recovery requires temporal information rather than spatial smoothing alone. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Preview of Denoise Input — detail-chart, Gaussian σ=5 — Actual file preview for Denoise Input — detail-chart, Gaussian σ=5

Denoise Input — detail-chart, Gaussian σ=5

Gaussian σ=5 applied to the detail-chart base plate with seed 9000. Light sensor noise — the level a modern camera produces at base ISO. Subtle enough that an over-aggressive denoiser does more damage than the noise did. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 19, where the light noise could otherwise be confused with compression artefacts.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Preview of Denoise Input — detail-chart, Gaussian σ=50 — Actual file preview for Denoise Input — detail-chart, Gaussian σ=50

Denoise Input — detail-chart, Gaussian σ=50

Gaussian σ=50 applied to the detail-chart base plate with seed 9051. Severe noise approaching the signal level. Included as the failure case — most denoisers hallucinate structure here, which is exactly what the paired reference exposes. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Preview of Denoise Input — detail-chart, Multiplicative speckle — Actual file preview for Denoise Input — detail-chart, Multiplicative speckle

Denoise Input — detail-chart, Multiplicative speckle

Multiplicative speckle applied to the detail-chart base plate with seed 9102. Multiplicative rather than additive noise, so its amplitude scales with local brightness — the pattern seen in ultrasound and radar. Additive-noise models systematically under-correct highlights. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Preview of Denoise Input — detail-chart, Poisson shot noise — Actual file preview for Denoise Input — detail-chart, Poisson shot noise

Denoise Input — detail-chart, Poisson shot noise

Poisson shot noise applied to the detail-chart base plate with seed 9119. Photon shot noise, signal-dependent and the physically correct model for low-light capture. Dark regions are proportionally far noisier than bright ones. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Filter the library

SearchTypeCategorySubcategoryFormatUse caseLive targetSort