Streaming Video Editing with Easy Adaptation

Researchers 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. The work systematically revisits existing video-to-video diffusion approaches to address the problem.

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 ap