Structure Preserving Diffusion Models

Diffusion models have become the leading distribution-learning method in recent years. Herein, we introduce structure-preserving diffusion processes, a family of diffusion processes for learning distributions that possess additional structure, such as group symmetries, by developing theoretical cond...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-02
Main Authors: Lu, Haoye, Szabados, Spencer, Yu, Yaoliang
Format: Article
Language:English
Subjects:
Data sampling
Learning
Symmetry
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Diffusion models have become the leading distribution-learning method in recent years. Herein, we introduce structure-preserving diffusion processes, a family of diffusion processes for learning distributions that possess additional structure, such as group symmetries, by developing theoretical conditions under which the diffusion transition steps preserve said symmetry. While also enabling equivariant data sampling trajectories, we exemplify these results by developing a collection of different symmetry equivariant diffusion models capable of learning distributions that are inherently symmetric. Empirical studies, over both synthetic and real-world datasets, are used to validate the developed models adhere to the proposed theory and are capable of achieving improved performance over existing methods in terms of sample equality. We also show how the proposed models can be used to achieve theoretically guaranteed equivariant image noise reduction without prior knowledge of the image orientation.
ISSN:2331-8422