Testaroo, Real, documented example files for testing

Colourisation Input: colour-patches, 50% Desaturated

The colour-patches plate with 50% of its saturation removed, leaving 50% of the original chroma. This is the faded-archive case rather than the black-and-white one: some colour information survives, so the task is restoration rather than invention, and a model that ignores the residual chroma is throwing away the strongest signal it has.

File: MP4 · Colour · 640x360
Use case: Video colourisationCompression artefacts+1· Conversion set

Colourisation Input: colour-patches, 80% Desaturated

The colour-patches plate with 80% of its saturation removed, leaving 19% of the original chroma. This is the faded-archive case rather than the black-and-white one: some colour information survives, so the task is restoration rather than invention, and a model that ignores the residual chroma is throwing away the strongest signal it has.

File: MP4 · Colour · 640x360
Use case: Video colourisationCompression artefacts+1· Conversion set

Colourisation Input: colour-patches, Rec. 601 luma

The colour-patches plate desaturated using Rec. 601 luma weights. Rec. 601 weights instead: the SD standard, and still the default in a surprising amount of software. The greys differ measurably from the 709 version, which is a good check on whether a pipeline knows which standard it is using.

File: MP4 · Colour · 640x360
Use case: Video colourisationVideo QA· Conversion set

Colourisation Input: colour-patches, Rec. 709 luma

The colour-patches plate desaturated using Rec. 709 luma weights. Converted with Rec. 709 luma weights, the correct coefficients for HD material. All chroma is gone, so a colouriser has nothing to recover from and must infer it entirely.

File: MP4 · Colour · 640x360
Use case: Video colourisationVideo QA· Conversion set

Colourisation Input: gradient-sky, 50% Desaturated

The gradient-sky plate with 50% of its saturation removed, leaving 50% of the original chroma. This is the faded-archive case rather than the black-and-white one: some colour information survives, so the task is restoration rather than invention, and a model that ignores the residual chroma is throwing away the strongest signal it has.

File: MP4 · Colour · 640x360
Use case: Video colourisationCompression artefacts+1· Conversion set

Colourisation Input: gradient-sky, 80% Desaturated

The gradient-sky plate with 80% of its saturation removed, leaving 19% of the original chroma. This is the faded-archive case rather than the black-and-white one: some colour information survives, so the task is restoration rather than invention, and a model that ignores the residual chroma is throwing away the strongest signal it has.

File: MP4 · Colour · 640x360
Use case: Video colourisationCompression artefacts+1· Conversion set

Colourisation Input: gradient-sky, Rec. 601 luma

The gradient-sky plate desaturated using Rec. 601 luma weights. Rec. 601 weights instead: the SD standard, and still the default in a surprising amount of software. The greys differ measurably from the 709 version, which is a good check on whether a pipeline knows which standard it is using.

File: MP4 · Colour · 640x360
Use case: Video colourisationVideo QA· Conversion set

Colourisation Input: gradient-sky, Rec. 709 luma

The gradient-sky plate desaturated using Rec. 709 luma weights. Converted with Rec. 709 luma weights, the correct coefficients for HD material. All chroma is gone, so a colouriser has nothing to recover from and must infer it entirely.

File: MP4 · Colour · 640x360
Use case: Video colourisationVideo QA· Conversion set

Colourisation Input: pan-city, 50% Desaturated

The pan-city plate with 50% of its saturation removed, leaving 50% of the original chroma. This is the faded-archive case rather than the black-and-white one: some colour information survives, so the task is restoration rather than invention, and a model that ignores the residual chroma is throwing away the strongest signal it has.

File: MP4 · Colour · 640x360
Use case: Video colourisationCompression artefacts+1· Conversion set

Colourisation Input: pan-city, 80% Desaturated

The pan-city plate with 80% of its saturation removed, leaving 19% of the original chroma. This is the faded-archive case rather than the black-and-white one: some colour information survives, so the task is restoration rather than invention, and a model that ignores the residual chroma is throwing away the strongest signal it has.

File: MP4 · Colour · 640x360
Use case: Video colourisationCompression artefacts+1· Conversion set

Colourisation Input: pan-city, Rec. 601 luma

The pan-city plate desaturated using Rec. 601 luma weights. Rec. 601 weights instead: the SD standard, and still the default in a surprising amount of software. The greys differ measurably from the 709 version, which is a good check on whether a pipeline knows which standard it is using.

File: MP4 · Colour · 640x360
Use case: Video colourisationVideo QA· Conversion set

Colourisation Input: pan-city, Rec. 709 luma

The pan-city plate desaturated using Rec. 709 luma weights. Converted with Rec. 709 luma weights, the correct coefficients for HD material. All chroma is gone, so a colouriser has nothing to recover from and must infer it entirely.

File: MP4 · Colour · 640x360
Use case: Video colourisationVideo QA· Conversion set

Compression Input: detail-chart at CRF 28

The detail-chart plate at CRF 28: mild artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the fine wedges collapse first, showing exactly which spatial frequencies the quantiser discarded.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: detail-chart at CRF 36

The detail-chart plate at CRF 36: clearly visible artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the fine wedges collapse first, showing exactly which spatial frequencies the quantiser discarded.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: detail-chart at CRF 44

The detail-chart plate at CRF 44: severe artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the fine wedges collapse first, showing exactly which spatial frequencies the quantiser discarded.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: detail-chart at CRF 51

The detail-chart plate at CRF 51 (extreme), the codec's limit artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the fine wedges collapse first, showing exactly which spatial frequencies the quantiser discarded.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: gradient-sky at CRF 28

The gradient-sky plate at CRF 28: mild artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the damage shows as banding across the smooth gradient, which is the artefact viewers notice first and metrics score most poorly.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: gradient-sky at CRF 36

The gradient-sky plate at CRF 36: clearly visible artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the damage shows as banding across the smooth gradient, which is the artefact viewers notice first and metrics score most poorly.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: gradient-sky at CRF 44

The gradient-sky plate at CRF 44: severe artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the damage shows as banding across the smooth gradient, which is the artefact viewers notice first and metrics score most poorly.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: gradient-sky at CRF 51

The gradient-sky plate at CRF 51 (extreme), the codec's limit artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the damage shows as banding across the smooth gradient, which is the artefact viewers notice first and metrics score most poorly.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: text-motion at CRF 28

The text-motion plate at CRF 28: mild artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the damage shows as ringing around glyph edges, where legibility gives a pass/fail signal that needs no metric.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: text-motion at CRF 36

The text-motion plate at CRF 36: clearly visible artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the damage shows as ringing around glyph edges, where legibility gives a pass/fail signal that needs no metric.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: text-motion at CRF 44

The text-motion plate at CRF 44: severe artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the damage shows as ringing around glyph edges, where legibility gives a pass/fail signal that needs no metric.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Compression Input: text-motion at CRF 51

The text-motion plate at CRF 51 (extreme), the codec's limit artefacts. Encoded from the original frames rather than transcoded from the reference, so it carries exactly one generation of loss and the comparison is clean. On this plate the damage shows as ringing around glyph edges, where legibility gives a pass/fail signal that needs no metric.

File: MP4 · Compress · 640x360
Use case: Compression artefactsVideo codecs+1· Conversion set

Explore the test library

Filter the library

444 results