Segmentation Ground Truth — Instance Masks
Per-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.
Specifications
- Resolution
- 640x360
- Fps
- 24
- Instances
- 3
- Encoding
- red = disc, green = square, blue = centre marker, black = background
- Note
- colour-coded per instance, not a binary foreground mask
- Role
- ground truth
- Crf
- 14
- Base Plate
- solids
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
“Segmentation Ground Truth — Instance Masks” is a deterministic Novus Examples fixture for Video segmentation, Video matting, Video QA. Hard-edged and anti-aliased subjects in motion, each shipped with the exact per-frame mask used to create it — for scoring video object segmentation and rotoscoping frame by frame instead of spot-checking.
Documented properties for this file: ground truth · 24 fps · red = disc, green = square, blue = centre marker, black = background. 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="instance-masks.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.
- mp4Matting Ground Truth — Per-Frame Alpha MatteThe 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.
- mp4Matting Input — Subject on Busy patternedThe same subject and the same alpha, composited over busy patterned — no chroma screen, which is the case a general background-removal model actually has to handle. Score the predicted alpha against the ground-truth matte in this group.
- mp4Matting Input — Subject on Colour close to subjectThe same subject and the same alpha, composited over colour close to subject — no chroma screen, which is the case a general background-removal model actually has to handle. The background colour deliberately sits close to the subject's own, so colour alone cannot separate them and the model must use shape and motion. Score the predicted alpha against the ground-truth matte in this group.
- mp4Matting Input — Subject on Dark studioThe same subject and the same alpha, composited over dark studio — no chroma screen, which is the case a general background-removal model actually has to handle. Score the predicted alpha against the ground-truth matte in this group.
Generated by generation/video_ai_suites.py. Free for any use, no attribution required — license.