ShapeNet: Shape Constraint for Galaxy Image Deconvolution

TL;DR

ShapeNet introduces a novel deep learning approach that incorporates shape constraints to improve galaxy image deconvolution, preserving physical features better than previous methods, and is applied to both optical and radio-interferometry data.

Contribution

This paper extends the Tikhonet framework by integrating shape constraints into deep learning for galaxy image deconvolution, including the first application to radio-interferometry data.

Findings

ShapeNet outperforms previous methods in preserving galaxy shape.

The approach effectively reduces pixel error in deconvolved images.

A new simulated radio data set is generated and shared with the community.

Abstract

Deep Learning (DL) has shown remarkable results in solving inverse problems in various domains. In particular, the Tikhonet approach is very powerful to deconvolve optical astronomical images (Sureau et al. 2020). Yet, this approach only uses the $\ell_2$ loss, which does not guarantee the preservation of physical information (e.g. flux and shape) of the object reconstructed in the image. In Nammour et al. (2021), a new loss function was proposed in the framework of sparse deconvolution, which better preserves the shape of galaxies and reduces the pixel error. In this paper, we extend Tikhonet to take into account this shape constraint, and apply our new DL method, called ShapeNet, to optical and radio-interferometry simulated data set. The originality of the paper relies on i) the shape constraint we use in the neural network framework, ii) the application of deep learning to radio-interferometry image deconvolution for the first time, and iii) the generation of a simulated radio data set that we make available for the community. A range of examples illustrates the results.