MotionPhys: Detecting AI-Generated Videos via Physical Consistency of Optical-Flow Trajectories
This work introduces MotionPhys, a lightweight and interpretable framework that treats sparse motion trajectories as physical evidence rather than relying on appearance artifacts or generator-specific traces and reveals subtle motion inconsistencies that are difficult to capture with conventional visual cues and transforms them into a compact representation for efficient detection.
Hao He, Hao Tan, Zichang Tan et al.
· 0 citations