Phase-aware video generation captures solid and gas interactions realistically
Phase-aware video generation for physics-grounded dynamics and interactions
Computer Vision and Pattern Recognition
Summary
Making videos that realistically show how solids and gases move together is hard because each behaves very differently but still affects the other. The authors made a new system called PAVG that separately models solid and gas movements while also linking them to reflect their interactions. They trained it on a huge set of simulated examples of solids, gases, and their combined behaviors. Their results show PAVG creates videos that move in more believable ways and look better than previous methods.
What this means in practice
- •For visual effects artists: Create more physically accurate animations of interactions between solids and gases for films and games using a phase-aware video generation tool.$Commercial implications: Enables studios to produce realistic solid-gas interaction effects, improving visual quality and reducing manual animation effort.
- •For robotics developers: Simulate and predict robot interactions with environments involving both solid objects and gases for safer and more effective control.
Authors
Jingfeng Ou, Kun Wang, Rui Zhao, Jingwei Guan, Limin Wang, Chao Dong, Xingyu Zeng
Abstract
Generating physically plausible videos for solid-gas dynamics is challenging as different phases exhibit distinct dynamics yet remain coupled through physical interactions. We present PAVG, a Phase-Aware Video Generator for solid-gas dynamics and interactions. It employs a dual-branch architecture to explicitly model the distinct dynamics of solids and gases, while spatiotemporal cross-attention captures their physical interactions. This design enables PAVG to preserve phasespecific motion characteristics while producing physically consistent responses across phases. To facilitate this task, we further construct a simulation corpus comprising over 700K physical trajectories across diverse solid, gas, and solid-gas interaction scenarios. Extensive evaluations demonstrate that our PAVG produces videos with improved motion adherence, physical plausibility, and visual quality compared with existing approaches.