Metraipolis › archive › dc_88643beab454

Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning — arXiv:2609.00656

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00656
License (as archived)
CC0-1.0
Archived
2026-10-17T07:10:56.271Z
SHA-256 of the archived text
1b05dfa087adbfe4d8f25d211292caab4a167380da5e5f12e3cf095fe4359c67
Stable URL of this page
https://metraipolis.com/documento/dc_88643beab454

How to cite

Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning — arXiv:2609.00656 — arXiv (en), https://arxiv.org/abs/2609.00656 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_88643beab454 (Metraipolis archive dc_88643beab454, sha256 1b05dfa087adbfe4d8f25d211292caab4a167380da5e5f12e3cf095fe4359c67)
BibTeX
@misc{dc88643beab454,
  title = {Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning — arXiv:2609.00656},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00656},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_88643beab454; sha256 1b05dfa087adbfe4d8f25d211292caab4a167380da5e5f12e3cf095fe4359c67},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00656. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physically Plausible Video Generation (PPVG) seeks to synthesize videos consistent with physical principles, yet remains challenging due to underspecified natural language conditioning. Advanced chain-of-thought (CoT) frameworks augment prompts with physical knowledge. However, such prompts describe physical phenomena holistically, overlooking intermediate states and transition dynamics. In this paper, we reformulate PPVG as event-centric generation by representing physical evolution as a chain of causally connected and physically constrained events. Our framework comprises three key modules: (1) Physics-driven Event Chain Reasoning. This module decomposes physical phenomena into causally connected events represented by evolving scene graphs. Formula-derived physical quantities are bound to relevant objects and interactions, characterizing the direction and magnitude of each event transition. (2) Transition-aware Routed Keyframe Conditioning. This module routes each event to a specialized keyframe synthesis operator for appearance variation or object transformation. Consecutive keyframes are injected as residual guidance during denoising, enabling smooth visual transitions between event-boundary states. (3) Physics-injected Contrastive Semantic Guidance. This module constructs physics-informed positive and counterfactual negative prompts for classifier-free guidance, steering generation toward plausible dynamics and away from physics-violating counterparts. Experiments on PhyGenBench, VideoPhy, PhyWorldBench, and Physics-IQ demonstrate that our framework generates videos with superior physical plausibility across diverse domains.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.00656 — 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 2026-10-17T07:00:58.916Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).