Metraipolis › archive › dc_aa2c19aa9e4f

BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal — arXiv:2608.20107

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.20107
License (as archived): CC0-1.0
Archived: 2026-10-18T12:04:46.652Z
SHA-256 of the archived text: 845d52df8a0e7b4084f2ebddc76ec63e6adaac2fe6cb362c8d7841b993160a91
Stable URL of this page: https://metraipolis.com/documento/dc_aa2c19aa9e4f

How to cite

BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal — arXiv:2608.20107 — arXiv (en), https://arxiv.org/abs/2608.20107 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa2c19aa9e4f (Metraipolis archive dc_aa2c19aa9e4f, sha256 845d52df8a0e7b4084f2ebddc76ec63e6adaac2fe6cb362c8d7841b993160a91)

BibTeX

@misc{dcaa2c19aa9e4f,
  title = {BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal — arXiv:2608.20107},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20107},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa2c19aa9e4f; sha256 845d52df8a0e7b4084f2ebddc76ec63e6adaac2fe6cb362c8d7841b993160a91},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20107. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in generative video models have significantly improved visual realism in video object removal, yet evaluation protocols still focus on masked region fidelity, treating removal as local inpainting. In real scenes, object removal is a causal intervention: eliminating an object also requires removing its induced physical effects, such as shadows, reflections, illumination changes, translucency, and dynamic traces. Existing benchmarks lack aligned clean references or remain limited to simplified synthetic settings, preventing systematic evaluation of causal consistency. We introduce BeyondMasks, a paired benchmark for causally consistent video object removal, consisting of temporally aligned synthetic and real world video pairs with clean background references. The dataset spans diverse photometric, geometric, volumetric, and dynamic interactions, and supports both mask based and instruction driven editing. We further propose CORE, a structured vision language model based evaluation protocol that jointly measures object disappearance and after effect consistency, aligning more closely with human judgments than existing metrics. Benchmarking state of the art methods reveals systematic failures in removing secondary physical effects despite high masked region fidelity, exposing a gap between visual plausibility and causal correctness. BeyondMasks reframes video object removal as causal scene consistency rather than local reconstruction and provides a unified framework for its evaluation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.20107 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T12:01:57.735Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).