On Diffusion Process in SE(3)-invariant Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Zihan, Liu, Ruiying, Zheng, Jiachen, Wang, Xiaoxue, Yu, Tianshu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910351033892864
author Zhou, Zihan
Liu, Ruiying
Zheng, Jiachen
Wang, Xiaoxue
Yu, Tianshu
author_facet Zhou, Zihan
Liu, Ruiying
Zheng, Jiachen
Wang, Xiaoxue
Yu, Tianshu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01430
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On Diffusion Process in SE(3)-invariant Space
Zhou, Zihan
Liu, Ruiying
Zheng, Jiachen
Wang, Xiaoxue
Yu, Tianshu
Machine Learning
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.
title On Diffusion Process in SE(3)-invariant Space
topic Machine Learning
url https://arxiv.org/abs/2403.01430