Browse video · Novus Examples

Super-Resolution Input — pan-city, ÷4 Bicubic

The pan-city plate downscaled 4× to 160x90 using a bicubic filter. The standard downscale in most benchmarks. Mild ringing at edges, and the filter most super-resolution models are trained to invert — so it flatters them. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 160x90
Use case: Video upscalingVideo QA· Conversion set

Super-Resolution Input — pan-city, ÷4 Nearest neighbour

The pan-city plate downscaled 4× to 160x90 using a nearest neighbour filter. Point sampling with no filtering at all, so downscaling aliases hard. The Siemens star folds into moiré, and no amount of upscaling can recover what aliasing destroyed. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 160x90
Use case: Video upscalingVideo QA· Conversion set

Super-Resolution Input — text-motion, ÷2 Area / box

The text-motion plate downscaled 2× to 320x180 using a area / box filter. Simple pixel averaging, what a camera's binning path actually does. Softer than bicubic and not what most models saw in training, which makes it a fairer test. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 320x180
Use case: Video upscalingVideo QA· Conversion set

Super-Resolution Input — text-motion, ÷2 Bicubic

The text-motion plate downscaled 2× to 320x180 using a bicubic filter. The standard downscale in most benchmarks. Mild ringing at edges, and the filter most super-resolution models are trained to invert — so it flatters them. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 320x180
Use case: Video upscalingVideo QA· Conversion set

Super-Resolution Input — text-motion, ÷2 Nearest neighbour

The text-motion plate downscaled 2× to 320x180 using a nearest neighbour filter. Point sampling with no filtering at all, so downscaling aliases hard. The Siemens star folds into moiré, and no amount of upscaling can recover what aliasing destroyed. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 320x180
Use case: Video upscalingVideo QA· Conversion set

Super-Resolution Input — text-motion, ÷3 Area / box

The text-motion plate downscaled 3× to 212x120 using a area / box filter. Simple pixel averaging, what a camera's binning path actually does. Softer than bicubic and not what most models saw in training, which makes it a fairer test. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 212x120
Use case: Video upscalingVideo QA· Conversion set

Super-Resolution Input — text-motion, ÷3 Bicubic

The text-motion plate downscaled 3× to 212x120 using a bicubic filter. The standard downscale in most benchmarks. Mild ringing at edges, and the filter most super-resolution models are trained to invert — so it flatters them. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 212x120
Use case: Video upscalingVideo QA· Conversion set

Super-Resolution Input — text-motion, ÷3 Nearest neighbour

The text-motion plate downscaled 3× to 212x120 using a nearest neighbour filter. Point sampling with no filtering at all, so downscaling aliases hard. The Siemens star folds into moiré, and no amount of upscaling can recover what aliasing destroyed. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 212x120
Use case: Video upscalingVideo QA· Conversion set

Super-Resolution Input — text-motion, ÷4 Area / box

The text-motion plate downscaled 4× to 160x90 using a area / box filter. Simple pixel averaging, what a camera's binning path actually does. Softer than bicubic and not what most models saw in training, which makes it a fairer test. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 160x90
Use case: Video upscalingVideo QA· Conversion set

Super-Resolution Input — text-motion, ÷4 Bicubic

The text-motion plate downscaled 4× to 160x90 using a bicubic filter. The standard downscale in most benchmarks. Mild ringing at edges, and the filter most super-resolution models are trained to invert — so it flatters them. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 160x90
Use case: Video upscalingVideo QA· Conversion set

Super-Resolution Input — text-motion, ÷4 Nearest neighbour

The text-motion plate downscaled 4× to 160x90 using a nearest neighbour filter. Point sampling with no filtering at all, so downscaling aliases hard. The Siemens star folds into moiré, and no amount of upscaling can recover what aliasing destroyed. Upscale it back to 640x360 and score against the ground truth in this group — the filter is recorded because which one was used changes the difficulty far more than the scale factor does.

File: MP4 · Superres · 160x90
Use case: Video upscalingVideo QA· Conversion set

Terminal Screencast Mock (MP4)

A screen-recording-style clip of a mock terminal — a window with traffic-light buttons and build output typing out line by line with a blinking cursor. A fixture for testing screen-capture pipelines, UI-motion thumbnails, and text-in-video OCR.

File: MP4 · Screencast · 480x300
Use case: Conversion testing

jpg

41.6 KB

Thumbnail Track — Sprite Sheet

A 6x2 sprite sheet of 160x90 scrub-preview thumbnails in a single JPEG. Players fetch one image rather than 12 separate requests, then crop each tile with a media fragment — which is why the WebVTT index in this group is the load-bearing half of the pair. Useless on its own; that is the point of shipping them together.

File: JPG · Thumbnails Track
Use case: Streaming manifestsVideo QA· Conversion set

Thumbnail Track — WebVTT Sprite Index

The WebVTT half of a scrub-preview pair: each cue covers a slice of the timeline and its payload is a media-fragment URL naming a rectangle of the sprite sheet. This is how seek-bar previews are delivered in practice, and the #xywh fragment syntax is the part players implement inconsistently — some resolve it relative to the VTT, others to the page, and some ignore the fragment entirely and show the whole sheet.

File: VTT · Thumbnails Track · 12 cues
Use case: Streaming manifestsSubtitle parsing+1· Conversion set

TS — MPEG-TS H.264 Clip

The clip as an MPEG transport stream (.ts) — the container behind HLS streaming and broadcast. For testing TS demuxing and HLS tooling.

File: TS · Ts · 480x270
Use case: Conversion testing

TTML — IMSC Nested Spans and Regions

TTML using the features broadcast caption profiles rely on: two layout regions, named styles including a text outline, a declared frame rate and media time base, and spans nested two deep so styles cascade. Converting this to SubRip necessarily flattens all of it. Tests whether a TTML implementation resolves style inheritance or only reads the leaf text.

File: TTML · Captions Edge
Use case: Subtitle parsingConversion testing+1· Conversion set

TTML — Intentionally Corrupt: Unclosed Element

An intentionally corrupt TTML document with an unclosed p element, making it not well-formed XML. Any conforming XML parser must reject it outright — which is exactly the useful property, since it distinguishes real XML parsing from regex-based caption scraping that would happily extract both cues.

File: TTML · Captions Corrupt
Use case: Subtitle parsingVideo QA· Conversion set

TXT — Video QC Note 10

Video QC companion SAMPLE (video-qc-checklist.txt) for Wave G suites.

File: TXT · Notes
Use case: Conversion testing

VAST 3.0 — Linear Ad With Companion Banners

A VAST 3.0 response pairing a linear spot with two companion banners in the standard IAB sizes, at the older schema version many ad servers still emit. Companions render alongside the video rather than in it, so they exercise a separate slot-matching path — the player has to find a matching container or correctly ignore them when required is none. All URLs point at example.invalid.

File: XML · Ad Signalling
Use case: Ad insertionStreaming manifests+1· Conversion set

VAST 4.2 — Empty (No Ad) Response

A valid VAST document containing no Ad element — the correct response when an ad server has nothing to serve. It arrives as HTTP 200 with a well-formed body, so it is not an error condition, and a player must resume content immediately rather than waiting for a timeout. Frequently mishandled: players stall on the break or log a spurious failure. The smallest meaningful VAST document there is.

File: XML · Ad Signalling
Use case: Ad insertionStreaming manifests+1· Conversion set

VAST 4.2 — Inline Linear Ad Response

A complete VAST 4.2 inline response for a linear pre-roll: two progressive MP4 media files at different bitrates, quartile tracking, an impression beacon and a click-through. Every URL points at the reserved example.invalid domain, so nothing can ever be fetched and no real ad server is contacted. For testing VAST parsing and player integration without a live ad stack.

File: XML · Ad Signalling · 00:00:15
Use case: Ad insertionStreaming manifests+1· Conversion set

VAST 4.2 — Wrapper (Redirect) Response

A VAST wrapper — a response that carries no media of its own, only a VASTAdTagURI pointing at another VAST document plus its own tracking beacons that must be fired in addition to the resolved ad's. Wrapper chains are where real ad integrations break: unbounded redirect depth, timeouts, and tracking dropped part-way down the chain. Pairs with the inline response it nominally redirects to.

File: XML · Ad Signalling
Use case: Ad insertionStreaming manifests+1· Conversion set

Vertical 9:16 Clip (MP4, 270x480)

A portrait 9:16 (270×480) clip with a vertically-moving marker — the aspect ratio of phone and short-form video. A fixture for testing vertical-video handling, orientation, and letterboxing in players and thumbnailers.

File: MP4 · Formats · 270x480
Use case: Conversion testingResolution testing

Video Clips Archive (ZIP)

A ZIP bundling the MP4 and WebM test clips with a README — a 'video archive' for testing pipelines that unpack an archive and then transcode its contents. Stored (not re-compressed), since the clips are already compressed.

File: ZIP · Bundle · 3 members
Use case: Conversion testing

Explore the test library

Filter the library

402 results