Paper
Geração de Imagem
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation
Video diffusion models are adapted to decode explicit surface primitives directly from latent space, enabling high-quality 3D scene generation with improved geometric accuracy and…
Hugging Face · Daily Papers
·Orest Kupyn, Goutam Bhat
·
·▲ 13 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Orest Kupyn, Goutam Bhat, Philipp Henzler, Fabian Manhardt, Christian Rupprecht, Federico Tombari
- 13 upvotes da comunidade
- Temas: video diffusion models, latent space, 3D Gaussians, triangle splats, ray-centered rotation parameterization, product window function
Resumo
Resumo original (em inglês), extraído do paper:
Video diffusion models are adapted to decode explicit surface primitives directly from latent space, enabling high-quality 3D scene generation with improved geometric accuracy and real-time rendering capabilities.
