Generative Adversarial Networks for Astronomical Images Generation

TL;DR

This paper demonstrates the use of Lightweight GANs to generate a large variety of realistic astronomical images, combining real datasets and web images to create diverse celestial visuals.

Contribution

It introduces a novel application of Lightweight GANs to generate extensive and diverse astronomical images from multiple datasets, including web-sourced and Galaxy Zoo data.

Findings

Generated thousands of new celestial images

Successfully combined real and synthetic data for diverse visuals

Code and images are publicly available

Abstract

Space exploration has always been a source of inspiration for humankind, and thanks to modern telescopes, it is now possible to observe celestial bodies far away from us. With a growing number of real and imaginary images of space available on the web and exploiting modern deep Learning architectures such as Generative Adversarial Networks, it is now possible to generate new representations of space. In this research, using a Lightweight GAN, a dataset of images obtained from the web, and the Galaxy Zoo Dataset, we have generated thousands of new images of celestial bodies, galaxies, and finally, by combining them, a wide view of the universe. The code for reproducing our results is publicly available at https://github.com/davide-coccomini/GAN-Universe, and the generated images can be explored at https://davide-coccomini.github.io/GAN-Universe/.