Solar Image Deconvolution by Generative Adversarial Network

TL;DR

This paper introduces a GAN-based deep learning method for deconvolving solar images obtained from aperture synthesis telescopes, significantly improving image clarity over traditional methods like CLEAN.

Contribution

The study presents a novel GAN-based approach specifically designed for solar image deconvolution, outperforming traditional algorithms in clarity and effectiveness.

Findings

GAN model outperforms CLEAN in solar image deconvolution

Deep learning approach enhances image resolution and reduces blur

Experimental results show significant improvement over traditional methods

Abstract

With Aperture synthesis (AS) technique, a number of small antennas can assemble to form a large telescope which spatial resolution is determined by the distance of two farthest antennas instead of the diameter of a single-dish antenna. Different from direct imaging system, an AS telescope captures the Fourier coefficients of a spatial object, and then implement inverse Fourier transform to reconstruct the spatial image. Due to the limited number of antennas, the Fourier coefficients are extremely sparse in practice, resulting in a very blurry image. To remove/reduce blur, "CLEAN" deconvolution was widely used in the literature. However, it was initially designed for point source. For extended source, like the sun, its efficiency is unsatisfied. In this study, a deep neural network, referring to Generative Adversarial Network (GAN), is proposed for solar image deconvolution. The experimental results demonstrate that the proposed model is markedly better than traditional CLEAN on solar images.