Preprint
Sep 2026
Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning
This paper reformulate PPVG as event-centric generation by representing physical evolution as a chain of causally connected and physically constrained events, and generates videos with superior physical plausibility across diverse domains.
Zi-Xuan Wang, Yi-Xin Hu, Wen Li et al.
· 1 citation
· ⚡1