Streaming Video Editing with Easy Adaptation
- 类型：arxiv
- 标识：2609.24788
- 链接：https://arxiv.org/abs/2609.24788
- 主分类：multimodal
- 形态：method
- TLDR：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
- 副分类：engineering
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-22-agent-rag-longcontext-candidates.json