Diffusion Models for Probabilistic Deconvolution of Galaxy Images

TL;DR

This paper introduces a classifier-free conditional diffusion model for PSF deconvolution of galaxy images, providing greater diversity in possible deconvolutions compared to traditional generative models.

Contribution

The paper presents a novel diffusion-based approach for galaxy image deconvolution that outperforms VAEs in diversity of generated solutions.

Findings

Diffusion model captures more diverse deconvolutions.

Outperforms VAEs in sample diversity.

Effective for PSF deconvolution in astronomy.

Abstract

Telescopes capture images with a particular point spread function (PSF). Inferring what an image would have looked like with a much sharper PSF, a problem known as PSF deconvolution, is ill-posed because PSF convolution is not an invertible transformation. Deep generative models are appealing for PSF deconvolution because they can infer a posterior distribution over candidate images that, if convolved with the PSF, could have generated the observation. However, classical deep generative models such as VAEs and GANs often provide inadequate sample diversity. As an alternative, we propose a classifier-free conditional diffusion model for PSF deconvolution of galaxy images. We demonstrate that this diffusion model captures a greater diversity of possible deconvolutions compared to a conditional VAE.