PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

PixWorld presents a unified pixel-space diffusion approach for 3D reconstruction and generation that overcomes limitations of latent-space methods through direct image-level superv…

Hugging Face · Daily Papers ·Sensen Gao, Zhaoqing Wang · ·▲ 33 upvotes

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

Autores: Sensen Gao, Zhaoqing Wang, Qihang Cao, Dongdong Yu, Changhu Wang, Jia-Wang Bian

  • 33 upvotes da comunidade
  • Temas: 3D reconstruction, 3D generation, latent space, pixel space, diffusion models, Variational Autoencoder

Resumo

Resumo original (em inglês), extraído do paper:

PixWorld presents a unified pixel-space diffusion approach for 3D reconstruction and generation that overcomes limitations of latent-space methods through direct image-level supervision and geometry-aware feature alignment.

Onde ler

compartilhar: