EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing

TL;DR

EditCtrl is a novel, efficient video editing framework that localizes computation to edited regions, significantly reducing costs and improving quality over existing methods.

Contribution

It introduces a local video context module and a lightweight global embedder, enabling real-time, high-quality, multi-region video editing with minimal computation.

Findings

EditCtrl is 10 times more compute-efficient than state-of-the-art methods.

It improves editing quality despite reduced computational cost.

Supports multi-region editing with text prompts and autoregressive content propagation.

Abstract

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 10 times more 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 autoregressive content propagation.