Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation
From MaRDI portal
Publication:6428867
arXiv2303.04772MaRDI QIDQ6428867FDOQ6428867
Authors: Paul Hagemann, Sophie Mildenberger, Lars Ruthotto, Gabriele Steidl, Nicole Tianjiao Yang 
Publication date: 8 March 2023
Abstract: Score-based diffusion models (SBDM) have recently emerged as state-of-the-art approaches for image generation. Existing SBDMs are typically formulated in a finite-dimensional setting, where images are considered as tensors of a finite size. This papers develops SBDMs in the infinite-dimensional setting, that is, we model the training data as functions supported on a rectangular domain. Besides the quest for generating images at ever higher resolution our primary motivation is to create a well-posed infinite-dimensional learning problem so that we can discretize it consistently on multiple resolution levels. We thereby hope to obtain diffusion models that generalize across different resolution levels and improve the efficiency of the training process. We demonstrate how to overcome two shortcomings of current SBDM approaches in the infinite-dimensional setting. First, we modify the forward process to ensure that the latent distribution is well-defined in the infinite-dimensional setting using the notion of trace class operators. Second, we illustrate that approximating the score function with an operator network, in our case Fourier neural operators (FNOs), is beneficial for multilevel training. After deriving the forward process in the infinite-dimensional setting and reverse processes for finite approximations, we show their well-posedness, derive adequate discretizations, and investigate the role of the latent distributions. We provide first promising numerical results on two datasets, MNIST and material structures. In particular, we show that multilevel training is feasible within this framework.
Has companion code repository: https://github.com/paullyonel/multileveldiff
Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Numerical aspects of computer graphics, image analysis, and computational geometry (65D18)
This page was built for publication: Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6428867)
