EditCtrl：面向实时生成式视频编辑的解耦局部与全局控制
EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing
把视频编辑的计算量从全视频上下文收缩到掩码 token 上，再用轻量全局上下文嵌入器补回时序一致性，这个「局部优先 + 全局轻量引导」的分解思路可直接迁移到任何基于扩散/流模型的视频修复、物体移除或区域重绘管线中，并支撑实时自回归传播。
原文依据 a novel local video context module that operates solely on masked tokens, yielding a computational cost proportional to the edit size
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论借助预训练视频基础模型，高保真生成式视频编辑的质量已显著提升。然而其计算开销是主要瓶颈：无论图像修复掩码多大，这些模型往往都要低效地处理完整视频上下文，即使编辑是稀疏且局部的。本文提出 EditCtrl，一种高效的视频图像修复控制框架，只在需要的位置进行计算。该方法的核心是一个新颖的局部视频上下文模块，它仅作用于被掩码的 token，使计算开销与编辑规模成正比。这种局部优先的生成随后由一个轻量的时序全局上下文嵌入器引导，以极小的额外开销保证全视频范围的上下文一致性。EditCtrl 不仅比最优的生成式编辑方法计算效率高 10 倍，甚至相比采用全注意力的方法还提升了编辑质量。最后，我们展示了 EditCtrl 所解锁的新能力，包括基于文本提示的多区域编辑与实时自回归内容传播。
英文原文摘要 1131 字符
High-fidelity generative video editing has seen significant quality improvements by leveraging pre-trained video foundation models. However, their computational cost is a major bottleneck, as they are often designed to inefficiently process the full video context regardless of the inpainting mask's size, even for sparse, localized edits. In this paper, we introduce EditCtrl, an efficient video inpainting control framework that focuses computation only where it is needed. Our approach features a novel local video context module that operates solely on masked tokens, yielding a computational cost proportional to the edit size. This local-first generation is then guided by a lightweight temporal global context embedder that ensures video-wide context consistency with minimal overhead. Not only is EditCtrl 10xmore compute efficient than state-of-the-art generative editing methods, it even improves editing quality compared to methods designed with full-attention. Finally, we showcase how EditCtrl unlocks new capabilities, including multi-region editing with text prompts and real-time autoregressive content propagation.