Problem
Research questions and friction points this paper is trying to address.
video editing
instruction-guided
subject-guided
unified framework
One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
🤖 AI Summary
本文提出EditVid框架，通过结合稀疏因果记忆、基于对应的后注意令牌注入和软潜变量混合方法，解决了在统一框架下实现高质量指令引导和主体引导的视频编辑问题。
📝 Abstract
Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing within a single unified framework remains challenging. We introduce EditVid, a training-free framework combining sparse causal memory for local coherence, correspondence-based post-attention token injection for long-range identity preservation, and soft latent blending for edit locality. The same framework supports instruction-guided and reference-guided edits, including style transfer, attribute modification, object insertion, part-level editing, and subject replacement. On FiVE, EditVid achieves 78.16 FiVE-Acc, compared with 58.95 for the strongest evaluated training-free baseline, while obtaining competitive results on IVEBench. A user study further shows a 51.8\% overall preference for EditVid over 7 competing methods.
Innovation
Methods, ideas, or system contributions that make the work stand out.
training-free framework
sparse causal memory
correspondence-based post-attention token injection
soft latent blending
🔎 Similar Papers
No similar papers found.
