Physics-Guided Motion Loss for Video Generation Model

Abstract

Current video diffusion models generate visually compelling content but often violate basic laws of physics, producing subtle artifacts like rubber-sheet deformations and inconsistent object motion. We introduce a frequency-domain physics prior that improves motion plausibility without modifying model architectures. Our method decomposes common rigid motions (translation, rotation, scaling) into lightweight spectral losses computed on a low-frequency subset. Applied to Open-Sora, MVDIT, and Hunyuan, our approach improves both motion accuracy and action recognition by ~11\% on average on OpenVID-1M (relative), while maintaining visual quality. User studies show 74--83\% preference for our physics-enhanced videos. It also reduces warping error by 22--37\% (depending on the backbone) and improves temporal consistency scores. These results indicate that simple, global spectral cues are an effective drop-in regularizer for physically plausible motion in video diffusion.