Bayesian Deconvolution of Astronomical Images with Diffusion Models: Quantifying Prior-Driven Features in Reconstructions

TL;DR

This paper introduces a Bayesian deconvolution method using diffusion models to enhance astronomical images, achieving HST-like resolution and quantifying uncertainty and prior-driven features in reconstructions.

Contribution

It presents a novel application of diffusion models with Bayesian inference for astronomical image deconvolution, enabling uncertainty quantification and dataset adaptability.

Findings

Achieved HST-quality resolution on ground-based data.

Quantified uncertainty in reconstructions.

Identified prior-driven features in images.

Abstract

Deconvolution of astronomical images is a key aspect of recovering the intrinsic properties of celestial objects, especially when considering ground-based observations. This paper explores the use of diffusion models (DMs) and the Diffusion Posterior Sampling (DPS) algorithm to solve this inverse problem task. We apply score-based DMs trained on high-resolution cosmological simulations, through a Bayesian setting to compute a posterior distribution given the observations available. By considering the redshift and the pixel scale as parameters of our inverse problem, the tool can be easily adapted to any dataset. We test our model on Hyper Supreme Camera (HSC) data and show that we reach resolutions comparable to those obtained by Hubble Space Telescope (HST) images. Most importantly, we quantify the uncertainty of reconstructions and propose a metric to identify prior-driven features in the reconstructed images, which is key in view of applying these methods for scientific purposes.