Metraipolis › archive › dc_31dfdf9526ca

MotionPhys: Detecting AI-Generated Videos via Physical Consistency of Optical-Flow Trajectories — arXiv:2608.20770

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.20770
License (as archived): CC0-1.0
Archived: 2026-10-18T10:52:55.406Z
SHA-256 of the archived text: 6530b058bfad1cde9f3267013641a3fbead16fff2aab6465b9a5bee34c7ce77a
Stable URL of this page: https://metraipolis.com/documento/dc_31dfdf9526ca

How to cite

MotionPhys: Detecting AI-Generated Videos via Physical Consistency of Optical-Flow Trajectories — arXiv:2608.20770 — arXiv (en), https://arxiv.org/abs/2608.20770 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31dfdf9526ca (Metraipolis archive dc_31dfdf9526ca, sha256 6530b058bfad1cde9f3267013641a3fbead16fff2aab6465b9a5bee34c7ce77a)

BibTeX

@misc{dc31dfdf9526ca,
  title = {MotionPhys: Detecting AI-Generated Videos via Physical Consistency of Optical-Flow Trajectories — arXiv:2608.20770},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20770},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31dfdf9526ca; sha256 6530b058bfad1cde9f3267013641a3fbead16fff2aab6465b9a5bee34c7ce77a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20770. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern AI video generation models can produce videos with high visual fidelity and seemingly smooth temporal transitions. However, visual realism does not necessarily imply physical motion consistency. Existing generative models mainly optimize distribution matching in pixel or latent spaces, without explicitly enforcing real-world constraints such as inertia, continuous forces, and trajectory geometry. Our experiments show that AI-generated videos remain visually plausible over short sequences of consecutive frames, yet fail to preserve physical motion consistency throughout a complete object action, resulting in systematic statistical discrepancies in their motion trajectories. Based on this observation, we introduce MotionPhys, a lightweight and interpretable framework that treats sparse motion trajectories as physical evidence rather than relying on appearance artifacts or generator-specific traces. By modeling the geometric evolution of trajectories across multiple temporal scales, MotionPhys reveals subtle motion inconsistencies that are difficult to capture with conventional visual cues and transforms them into a compact representation for efficient detection. Experiments on multiple datasets show that MotionPhys can effectively detect physical inconsistencies in generated videos and generalizes well across different video generators.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.20770 — 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 2026-10-18T10:48:13.565Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).