LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

A novel streaming video editing framework enables causal, frame-by-frame editing with stable long-horizon preservation and real-time responsiveness through a three-stage distillati…

Hugging Face · Daily Papers ·Xinyu Wang, Chongbo Zhao · ·▲ 70 upvotes

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Xinyu Wang, Chongbo Zhao, Fangneng Zhan, Yue Ma

  • 70 upvotes da comunidade
  • Temas: streaming video editing, causal editing, frame-by-frame editing, content preservation, real-time responsiveness, three-stage distillation pipeline

Resumo

Resumo original (em inglês), extraído do paper:

A novel streaming video editing framework enables causal, frame-by-frame editing with stable long-horizon preservation and real-time responsiveness through a three-stage distillation pipeline and AR-oriented mask cache.

Onde ler

compartilhar: