Matting Ground Truth — Per-Frame Alpha Matte
The exact per-frame alpha used to composite every clip in this group, as an 8-bit greyscale clip: white is opaque subject, black is background, and edges carry genuine intermediate values because the matte is anti-aliased rather than binary. This is what makes matting output measurable — compare a predicted alpha against this frame by frame instead of inspecting a composite and forming an opinion.
Specifications
- Resolution
- 640x360
- Fps
- 24
- Content
- 8-bit greyscale alpha
- White
- fully opaque subject
- Black
- fully transparent background
- Edges
- anti-aliased — not a binary mask
- Role
- ground truth
- Crf
- 14
- Base Plate
- subject
What is a .mp4 file?
MP4 (MPEG-4 Part 14) is a widely supported multimedia container based on ISOBMFF that holds video, audio, subtitles, and metadata, most commonly H.264 or H.265 video with AAC audio. It supports streaming, chapters, and multiple tracks. It is the dominant format for distributing and playing digital video.
How to use this file
Use an example MP4 to test container demuxing, track and codec detection, seeking and streaming, and transcoding or thumbnail-extraction pipelines.
How to use this file for testing
“Matting Ground Truth — Per-Frame Alpha Matte” is a deterministic Novus Examples fixture for Video matting, Video segmentation, Video QA. Moving subjects over known backgrounds, shipped with the exact alpha matte used to composite them — for scoring background removal and green-screen keying frame by 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="alpha-ground-truth.mp4"></video>Related files
- mp4Base Plate — Orbit — Hard-Edged SolidsA green disc and a red square orbiting the centre in antiphase over a grid. Hard edges and flat fills make the boundary unambiguous, so segmentation and tracking output can be scored against exact geometry rather than a judgement call. One of eight shared base plates: every AI-video suite in this library degrades one of these rather than inventing its own footage, so results across suites are comparable. Encoded at CRF 14 — well above the house CRF 30 — because a reference compressed as hard as the material under test puts the measurement floor above the effect being measured.
- mp4Base Plate — Subject on Chroma FieldAn anti-aliased figure moving over a chroma-green field with a deliberate lighting falloff, so the key is not perfectly flat. Ships with a per-frame alpha ground truth, which is what makes matting output measurable instead of merely inspectable. One of eight shared base plates: every AI-video suite in this library degrades one of these rather than inventing its own footage, so results across suites are comparable. Encoded at CRF 14 — well above the house CRF 30 — because a reference compressed as hard as the material under test puts the measurement floor above the effect being measured.
- mp4Segmentation Ground Truth — Instance MasksPer-frame instance masks for the orbit plate, colour-coded so the three objects are separable: red is the disc, green the square, blue the centre marker, black the background. Instance identity is stable across frames, which is what makes this usable for video object segmentation and tracking rather than only per-frame segmentation. Note the mask is encoded lossily like every other clip here, so threshold rather than testing for exact equality.
- mp4Segmentation Input — Trimap (Foreground / Unknown / Background)A three-level trimap derived from the instance masks: definite foreground, definite background, and a nine-pixel unknown band around every boundary. This is the input interactive matting and rotoscoping tools actually take, and the band is where all the difficulty lives — a matte is only as good as its handling of that region.
- webmAlpha Channel — VP9 in WebMVideo with a real per-pixel alpha channel: VP9 yuva420p in WebM, the one alpha path browsers decode natively. Composite it over a page background and the transparency is genuine, not a chroma key. Roughly 90% of each frame is fully transparent. Two traps this file exists to expose. First, auto-alt-ref must be disabled at encode time or libvpx silently drops the alpha plane, producing a valid file with no transparency and no error. Second, WebM stores VP9 alpha in BlockAdditional and signals it with AlphaMode=1, so FFmpeg's NATIVE vp9 decoder reports pix_fmt yuv420p and decodes fully opaque — you must force `-c:v libvpx-vp9` to see the alpha at all. Probing this file with default settings and concluding it has no alpha is the expected mistake.
- mp4Segmentation Input — Orbiting SolidsTwo hard-edged objects orbiting in antiphase over a grid, plus a static centre marker. The objects cross in front of the grid and reach the frame edges, so occlusion and boundary handling both get exercised. Every frame has an exact mask in this group.
Generated by generation/video_ai_suites.py. Free for any use, no attribution required — license.