Jun 2026
SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models
Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated motions often violate physical plausibility. We observe a common kinematic failure,"motion entanglement", the unintended coupling of independent motion sources, such as camera movement and object motion. We identify tha...
Ruoyu Wang, Jialun Liu, Huayang Huang et al.
· arXiv.org · 1 citation