Solving Inverse Problems for Spectral Energy Distributions with Deep Generative Networks

TL;DR

This paper introduces a novel deep generative network approach to reconstruct complex astronomical spectral energy distributions from limited or unreliable measurements, overcoming challenges posed by the lack of local properties in SEDs.

Contribution

It extends deep generative inverse problem techniques from images to spectral energy distributions, using a Generative Latent Optimization model trained with limited and corrupted data.

Findings

Successful reconstruction of SEDs from scarce measurements

Extension of generative inverse methods to non-image data

Effective training with limited and corrupted data

Abstract

We propose an end-to-end approach for solving inverse problems for a class of complex astronomical signals, namely Spectral Energy Distributions (SEDs). Our goal is to reconstruct such signals from scarce and/or unreliable measurements. We achieve that by leveraging a learned structural prior in the form of a Deep Generative Network. Similar methods have been tested almost exclusively for images which display useful properties (e.g., locality, periodicity) that are implicitly exploited. However, SEDs lack such properties which make the problem more challenging. We manage to successfully extend the methods to SEDs using a Generative Latent Optimization model trained with significantly fewer and corrupted data.