PhysiFormer: Learning to Simulate Mechanics in World Space
PhysiFormer uses coordinate-space diffusion to generate physically-plausible 3D object motions without explicit inductive biases, enabling efficient multi-object reasoning and gene…
Hugging Face · Daily Papers
·Yiming Chen, Yushi Lan
·
·▲ 9 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Yiming Chen, Yushi Lan, Andrea Vedaldi
- 9 upvotes da comunidade
- Temas: diffusion transformer, 3D meshes, world coordinates, vertex trajectories, denoising diffusion process, probabilistic formulation
Resumo
Resumo original (em inglês), extraído do paper:
PhysiFormer uses coordinate-space diffusion to generate physically-plausible 3D object motions without explicit inductive biases, enabling efficient multi-object reasoning and generalization to complex materials and geometries.Onde ler
// relacionados
