Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing 事件

Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing arXiv:2605.23192v2 Announce Type: replace Abstract: Video editing has recently achieved remarkable progress with diffusion-based generative models, enabling diverse object-level manipulations from natural language instructions. However, existing methods often struggle under occlusion, viewpoint changes, and fast object motion, where unreliable visual observations lead to inaccurate localization, temporal flickering, an