الملخص
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.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Huang, H., Liu, Y., You, C., Martin, D., Zou, C., & Chen, W. (2026). Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training. https://omanscience.com/ar/articles/fluid-gen-zero-grounding-pretrained-video-generators-in-physics-without-training
MLA 9
Huang, Hong, et al. "Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training." https://omanscience.com/ar/articles/fluid-gen-zero-grounding-pretrained-video-generators-in-physics-without-training.
شيكاغو (المؤلف–التاريخ)
Huang, Hong, Yuqiu Liu, Chenyu You, Daniel Martin, Chuhang Zou, and Wuyang Chen. 2026. "Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training." https://omanscience.com/ar/articles/fluid-gen-zero-grounding-pretrained-video-generators-in-physics-without-training.
هارفارد
Huang, H., Liu, Y., You, C., Martin, D., Zou, C. and Chen, W. (2026) 'Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training', Available at: https://omanscience.com/ar/articles/fluid-gen-zero-grounding-pretrained-video-generators-in-physics-without-training.
فانكوفر
Huang H, Liu Y, You C, Martin D, Zou C, Chen W. Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training. https://omanscience.com/ar/articles/fluid-gen-zero-grounding-pretrained-video-generators-in-physics-without-training
IEEE
H. Huang, Y. Liu, C. You, D. Martin, C. Zou, and W. Chen, "Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training," https://omanscience.com/ar/articles/fluid-gen-zero-grounding-pretrained-video-generators-in-physics-without-training.