On Diffusion Process in SE(3)-invariant Space
Zhou, Zihan, Liu, Ruiying, Zheng, Jiachen, Wang, Xiaoxue, Yu, Tianshu
–arXiv.org Artificial Intelligence
Sampling viable 3D structures (e.g., molecules and point clouds) with SE(3)-invariance using diffusion-based models proved promising in a variety of real-world applications, wherein SE(3)-invariant properties can be naturally characterized by the inter-point distance manifold. However, due to the non-trivial geometry, we still lack a comprehensive understanding of the diffusion mechanism within such SE(3)-invariant space. This study addresses this gap by mathematically delineating the diffusion mechanism under SE(3)-invariance, via zooming into the interaction behavior between coordinates and the inter-point distance manifold through the lens of differential geometry. Upon this analysis, we propose accurate and projection-free diffusion SDE and ODE accordingly. Such formulations enable enhancing the performance and the speed of generation pathways; meanwhile offering valuable insights into other systems incorporating SE(3)-invariance.
arXiv.org Artificial Intelligence
Mar-3-2024
- Country:
- Europe > Denmark
- North Jutland > Aalborg (0.04)
- Asia > China
- Guangdong Province > Shenzhen (0.04)
- Hong Kong (0.04)
- Europe > Denmark
- Genre:
- Research Report (0.50)
- Technology: