Vera: A Layered Diffusion Model for Content-Preserving Video Editing
Vera is a layered diffusion framework that preserves video content during editing by generating edit layers and alpha mattes through a Mixture-of-Transformers architecture.
Hugging Face · Daily Papers
·Hongkai Zheng, Ta-Ying Cheng
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Hongkai Zheng, Ta-Ying Cheng, Benjamin Klein, Yisong Yue, Zhuoning Yuan
- 3 upvotes da comunidade
- Temas: video diffusion models, content preservation, layered diffusion framework, edit layer, alpha matte, compositing
Resumo
Resumo original (em inglês), extraído do paper:
Vera is a layered diffusion framework that preserves video content during editing by generating edit layers and alpha mattes through a Mixture-of-Transformers architecture.
