Metraipolis › archive › dc_3fa8fbb81b4d

PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos — arXiv:2609.38377

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38377
License (as archived)
CC0-1.0
Archived
2026-10-07T14:45:14.669Z
SHA-256 of the archived text
aeaf7eb03db0a2cdd74a3d032aefc95dc893ab92389214b8d2a72837f2bd6474
Stable URL of this page
https://metraipolis.com/documento/dc_3fa8fbb81b4d

How to cite

PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos — arXiv:2609.38377 — arXiv (en), https://arxiv.org/abs/2609.38377 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3fa8fbb81b4d (Metraipolis archive dc_3fa8fbb81b4d, sha256 aeaf7eb03db0a2cdd74a3d032aefc95dc893ab92389214b8d2a72837f2bd6474)
BibTeX
@misc{dc3fa8fbb81b4d,
  title = {PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos — arXiv:2609.38377},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38377},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3fa8fbb81b4d; sha256 aeaf7eb03db0a2cdd74a3d032aefc95dc893ab92389214b8d2a72837f2bd6474},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38377. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Evaluating the physical consistency of generated videos remains a fundamental challenge. Existing approaches rely on off-the-shelf vision-language models, which can often be myopic to physical dynamics, or fine-tuned evaluators trained on human annotations, which overfit to dataset-specific cues and fail to generalize. A key challenge is that existing supervision sources provide either relative ordering or absolute scores, but not both reliably and consistently across varied settings. To this end, we introduce PhyProbe, an evaluator that extracts features from a frozen pretrained spatio-temporal encoder and maps them to a scalar physical consistency violation score via a lightweight scoring head. PhyProbe is trained through a unified objective combining pairwise ranking, regression on noisy scalar annotations, and anchor-based calibration over a curated set of heterogeneous supervision sources. Experiments show that PhyProbe outperforms prior methods on most pairwise benchmarks spanning real-generated and generated-generated pairs under varying correspondence, with the largest gains in no-correspondence and generated-generated settings where existing fine-tuned evaluators degrade sharply. PhyProbe achieves strong correlation with human judgments, with close agreement between rank-based and linear metrics, indicating that scores are both well ordered and anchored to a stable [0, 1] scale. Further, despite being trained on supervision indicative of physical consistency, without explicit general-preference labels, PhyProbe also performs competitively on human preference benchmarks: consistent with the observation that physics violations are entangled with broader quality degradations.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.38377 — 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 2026-10-07T14:19:00.548Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).