Deep Learning-based galaxy image deconvolution

TL;DR

This paper introduces a deep learning-based galaxy image deconvolution method using the Learnlet transform, aiming to improve the speed and accuracy of astronomical image reconstruction for large-scale surveys.

Contribution

It proposes a novel deconvolution approach combining Tikhonov deconvolution with neural network post-processing, and compares different Unet architectures for astrophysical image deconvolution.

Findings

Learnlet-based method outperforms traditional techniques.

Neural networks effectively improve deconvolution quality.

Method adapts well to various noise levels.

Abstract

With the onset of large-scale astronomical surveys capturing millions of images, there is an increasing need to develop fast and accurate deconvolution algorithms that generalize well to different images. A powerful and accessible deconvolution method would allow for the reconstruction of a cleaner estimation of the sky. The deconvolved images would be helpful to perform photometric measurements to help make progress in the fields of galaxy formation and evolution. We propose a new deconvolution method based on the Learnlet transform. Eventually, we investigate and compare the performance of different Unet architectures and Learnlet for image deconvolution in the astrophysical domain by following a two-step approach: a Tikhonov deconvolution with a closed-form solution, followed by post-processing with a neural network. To generate our training dataset, we extract HST cutouts from the CANDELS survey in the F606W filter (V-band) and corrupt these images to simulate their blurred-noisy versions. Our numerical results based on these simulations show a detailed comparison between the considered methods for different noise levels.