LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
arXiv:2606.26740
The paper introduces LiveEdit, a diffusion‑based streaming video editing system that edits videos frame‑by‑frame in real time while preserving background stability, using a three‑stage distillation from a bidirectional model to an efficient unidirectional editor and an AR‑oriented mask cache to speed up inference.
Abstract
Streaming video editing has made rapid progress, yet practical deployment is still limited by two core issues: maintaining stable backgrounds and non-edited regions over time, and achieving the low latency required for real-time interactive scenarios. Meanwhile, recent streaming video generation methods are mostly developed for synthesis and cannot be directly applied to editing due to the strict preservation requirement and region-specific control. In this work, we present a novel streaming video editing framework that performs causal, frame-by-frame editing with strong content preservation and real-time responsiveness. Our key design is a three-stage distillation pipeline that progressively transfers editing capability from a powerful bidirectional foundation model to an efficient unidirectional streaming editor, enabling stable long-horizon edits without sacrificing visual fidelity. To further support real-time deployment, we introduce an AR-oriented mask cache that reuses region-related computation across frames, substantially reducing redundant processing and accelerating inference. Finally, we establish a dedicated benchmark for streaming video editing. Extensive evaluations demonstrate that our method achieves state-of-the-art visual quality among streaming baselines while drastically boosting inference speed to 12.66 FPS, making it suitable for interactive and augmented reality applications.
Accepted by ECCV 2026, Project page: https://live-edit.github.io