# Diffusion Models for Probabilistic Deconvolution of Galaxy Images

arXiv: https://arxiv.org/abs/2307.11122 · HTML: https://mlsanity.com/paper/2307.11122/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 20 Jul 2023.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [Solving Inverse Problems in Medical Imaging with Score-Based Generative Models](https://mlsanity.com/paper/2111.08005/) (2021)
- [Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit](https://mlsanity.com/paper/1702.00403/) (2017)
- [Posterior samples of source galaxies in strong gravitational lenses with score-based priors](https://mlsanity.com/paper/2211.03812/) (2022)
- [Probabilistic Mass Mapping with Neural Score Estimation](https://mlsanity.com/paper/2201.05561/) (2022)
- [Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks](https://mlsanity.com/paper/1811.03081/) (2018)
- [Strong Lensing Source Reconstruction Using Continuous Neural Fields](https://mlsanity.com/paper/2206.14820/) (2022)

## Built on by (most cited first, 4 of 4)

- [PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation](https://mlsanity.com/paper/2402.04355/) (2024)
- [Understanding Galaxy Morphology Evolution Through Cosmic Time via Redshift Conditioned Diffusion Models](https://mlsanity.com/paper/2411.18440/) (2024)
- [Blind Strong Gravitational Lensing Inversion: Joint Inference of Source and Lens Mass with Score-Based Models](https://mlsanity.com/paper/2511.04792/) (2025)
- [AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data](https://mlsanity.com/paper/2506.08306/) (2025)

## Abstract (arXiv)

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.