Metraipolis › archive › dc_2f4b6dca22c3

Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training — arXiv:2610.10984

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10984
License (as archived)
CC0-1.0
Archived
2026-10-09T06:30:12.857Z
SHA-256 of the archived text
98741eb2b7ca4572b6308ac0f0be60ae65ec67b13ba4b6452978fdf8f6bd2b9d
Stable URL of this page
https://metraipolis.com/documento/dc_2f4b6dca22c3

How to cite

Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training — arXiv:2610.10984 — arXiv (en), https://arxiv.org/abs/2610.10984 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f4b6dca22c3 (Metraipolis archive dc_2f4b6dca22c3, sha256 98741eb2b7ca4572b6308ac0f0be60ae65ec67b13ba4b6452978fdf8f6bd2b9d)
BibTeX
@misc{dc2f4b6dca22c3,
  title = {Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training — arXiv:2610.10984},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10984},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f4b6dca22c3; sha256 98741eb2b7ca4572b6308ac0f0be60ae65ec67b13ba4b6452978fdf8f6bd2b9d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10984. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present Fluid-Gen-Zero, a training-free framework for physics-aware fluid-object interaction video generation that decouples physical reasoning from appearance synthesis. Our key insight is to delegate motion dynamics to a physics simulator while preserving the appearance modeling capacity of pretrained video generators. We bridge these two domains through a two-level agentic workflow: generation-time planning, where a vision-language model (VLM) agent interprets intent and the simulation rollout to organize generation clips, and latent-space guidance, which injects simulation signals into denoising through region-aware latent wrapping. This plug-and-play design is compatible with current video foundation models. We further introduce a benchmark for fluid-object interaction video generation. Across Tora (CogVideoX-based), VACE and WanMove (Wan-based), Fluid-Gen-Zero consistently improves simulation alignment, reducing object trajectory error by 26.7%-81.5% and fluid fEPE (fluid flow endpoint error) by 67.9%-84.0%, while largely preserving perceptual quality. In a human preference study, raters favor Fluid-Gen-Zero in 55.1%-74.4% of same-backbone comparisons across three backbones, and in 90.4%-94.2% of comparisons against simulation-based methods. Code and data will be released upon acceptance.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2610.10984 — 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 2026-10-09T05:55:07.001Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).