SOURCE-LINKED INTELLIGENCE

Streaming Video Editing with Easy Adaptation

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

In this paper, we propose SVEET, a framework that requires merely training on a pretrained bidirectional video diffusion model but supports high-quality streaming video editing in an auto-regressive fashion. To tackle this problem, we first systematically revisit existing video-to-video diffusion approaches and identify two key principles for such streaming adaptation: backbone feature disentanglement and conditional frame independence. Building on these insights, we develop a novel paradigm for controllable video generation. At its core, an auxiliary model branch encodes source video inputs w

Read original source ↗ Open in workspace

recordType

paper

region

Global