LiveEdit：迈向基于扩散的实时流式视频编辑
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
AI总结：
提出一种因果逐帧编辑的流式视频框架，通过三阶段蒸馏将双向模型能力迁移至单向流式编辑器，结合AR掩码缓存实现12.66 FPS的实时编辑，并保持背景稳定。
摘要：
流式视频编辑已取得快速进展，但实际部署仍受两个核心问题限制：随时间维持稳定背景和非编辑区域，以及实现实时交互场景所需的低延迟。同时，最近的流式视频生成方法主要针对合成开发，由于严格的保留要求和区域特定控制，无法直接应用于编辑。在这项工作中，我们提出了一种新颖的流式视频编辑框架，该框架执行因果的逐帧编辑，具有强内容保留和实时响应能力。我们的关键设计是一个三阶段蒸馏流程，逐步将编辑能力从强大的双向基础模型转移到高效的单向流式编辑器，从而在不牺牲视觉保真度的情况下实现稳定的长时编辑。为了进一步支持实时部署，我们引入了一种面向AR的掩码缓存，跨帧重用区域相关计算，显著减少冗余处理并加速推理。最后，我们建立了一个专门的流式视频编辑基准。大量评估表明，我们的方法在流式基线中实现了最先进的视觉质量，同时将推理速度大幅提升至12.66 FPS，使其适用于交互式和增强现实应用。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
