What do the RVM, MatAnyone and MatAnyone 2 papers report on video-matting benchmarks (MAD, MSE, Grad, Conn, dtSSD), how do synthetic and real-video numbers differ, what limits do they state, and what are the code and weights licences?

RVM (arXiv v1, GPL-3.0 code) is auxiliary-free human matting and states it fails when people are in the background. MatAnyone (v2) and MatAnyone 2 (v2) are mask-guided: they take a first-frame mask, MatAnyone states it has the best MAD and dtSSD on every synthetic benchmark block (not every MSE or Grad), and it says the older VideoMatte240K ground truth lacks fine detail such as hair. Numbers do not transfer between benchmarks: MatAnyone reports core-region MAD 0.14 on a real-video benchmark with segmentation-mask ground truth, while MatAnyone 2 reports MatAnyone at MAD 5.76 on 19 real videos with manually annotated alpha every 10 frames. Even the newest model has 15.2% of boundary-band pixels flagged unreliable by the paper's own learned evaluator, whose checkpoint is not released at the pinned README. MatAnyone and MatAnyone 2 code carries the non-commercial S-Lab licence. Curator qualifications: Verified. Rights: MatAnyone and MatAnyone 2 code are S-Lab non-commercial; their weights inherit only the README's 'this project' wording, and the HF card has no licence field, so weight terms stay unclear. RVM code is GPL-3.0, with no weights licence line. Agents should not treat these as commercially usable. The 0.14-vs-0.19 MatAnyone real-benchmark MAD discrepancy across the two papers is kept unreconciled. Rights/verification notes are shown as limitations (L00 0019/ADR-0011): they restrict reuse of the cited material or record what was not verified; they are not cleared by this summary. Limitations: [component_reuse_restriction] Non-commercial code licence (S-Lab) for MatAnyone/MatAnyone 2. [component_reuse_restriction] Weights licences unclear for RVM and MatAnyone. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://arxiv.org/abs/2108.11515v1",
      "note": "head; head; Table 2; Table 7 / C.1"
    },
    {
      "url": "https://arxiv.org/abs/2501.14677v2",
      "note": "head; head; Table 2; Table 7 / C.1"
    },
    {
      "url": "https://arxiv.org/abs/2512.11782v2",
      "note": "head; head; Table 2; Table 7 / C.1"
    },
    {
      "url": "https://github.com/pq-yang/MatAnyone2/blob/0079197acd6d16a741f71558809c06c586c579e0/README.md",
      "note": "head; head; Table 2; Table 7 / C.1"
    },
    {
      "url": "https://github.com/pq-yang/MatAnyone/blob/e5ddc534c1fff9bb9e54cf476095d29071b7cb4f/LICENSE",
      "note": "head; head; Table 2; Table 7 / C.1"
    },
    {
      "url": "https://github.com/pq-yang/MatAnyone/blob/e5ddc534c1fff9bb9e54cf476095d29071b7cb4f/README.md",
      "note": "head; head; Table 2; Table 7 / C.1"
    },
    {
      "url": "https://github.com/PeterL1n/RobustVideoMatting/blob/53d74c6826735f01f4406b5ca9075eee27bec094/README.md",
      "note": "head; head; Table 2; Table 7 / C.1"
    },
    {
      "url": "https://huggingface.co/PeiqingYang/MatAnyone",
      "note": "head; head; Table 2; Table 7 / C.1"
    }
  ]
}