MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing

MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing

A video diffusion framework generates long, multi-view consistent videos by combining temporal and view-wise autoregression through 4D geometric bridging and spatio-temporal distil…

Hugging Face · Daily Papers ·Gal Fiebelman, Hadar Averbuch-Elor · ·▲ 3 upvotes

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

Autores: Gal Fiebelman, Hadar Averbuch-Elor, Sagie Benaim

  • 3 upvotes da comunidade
  • Temas: video diffusion models, temporal autoregression, multi-view synthesis, bidirectional attention, 4D geometric bridge, autoregressive 3D reconstruction model

Resumo

Resumo original (em inglês), extraído do paper:

A video diffusion framework generates long, multi-view consistent videos by combining temporal and view-wise autoregression through 4D geometric bridging and spatio-temporal distillation techniques.

Onde ler

compartilhar: