AI RESEARCH
Beyond Rigid: Benchmarking Non-Rigid Video Editing
arXiv CS.CV
•
ArXi:2601.18340v2 Announce Type: replace As video generation models are increasingly expected to manipulate physical dynamics, there is a growing need to move evaluation beyond appearance fidelity and semantic alignment. Non-rigid video editing offers a uniquely revealing testbed, where distinct materials impose distinct physical constraints. In this paper, we