2024/05/30 by Zhen Yang, Chen, Feng, Bohan Zhuang +4 · 3 citations
Computer Science · Social Sciences · #Computer Vision and Pattern Recognition (cs.CV) #Digital Rights Management and Security #FOS: Computer and information sciences #Multimedia Communication and Technology
paper · pdf · doi:10.48550/arxiv.2405.19726
openalex publication_date 2024/05/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present a novel task called online video editing, which is designed to edit streaming frames while maintaining temporal consistency. Unlike existing offline video editing assuming all frames are pre-established and accessible, online video editing is tailored to real-life applications such as live streaming and online chat, requiring (1) fast continual step inference, (2) long-term temporal modeling, and (3) zero-shot video editing capability. To solve these issues, we propose Streaming Video Diffusion (SVDiff), which incorporates the compact spatial-aware temporal recurrence into off-the-shelf Stable Diffusion and is trained with the segment-level scheme on large-scale long videos. This simple yet effective setup allows us to obtain a single model that is capable of executing a broad range of videos and editing each streaming frame with temporal coherence. Our experiments indicate that our model can edit long, high-quality videos with remarkable results, achieving a real-time inference speed of 15.2 FPS at a resolution of 512x512.