# Learning the Night Sky with Deep Generative Priors

arXiv: https://arxiv.org/abs/2302.02030 · HTML: https://mlsanity.com/paper/2302.02030/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 1 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Built on by (most cited first, 1 of 1)

- [AstroClearNet: Deep image prior for multi-frame astronomical image restoration](https://mlsanity.com/paper/2504.06463/) (2025)

## Abstract (arXiv)

Recovering sharper images from blurred observations, referred to as deconvolution, is an ill-posed problem where classical approaches often produce unsatisfactory results. In ground-based astronomy, combining multiple exposures to achieve images with higher signal-to-noise ratios is complicated by the variation of point-spread functions across exposures due to atmospheric effects. We develop an unsupervised multi-frame method for denoising, deblurring, and coadding images inspired by deep generative priors. We use a carefully chosen convolutional neural network architecture that combines information from multiple observations, regularizes the joint likelihood over these observations, and allows us to impose desired constraints, such as non-negativity of pixel values in the sharp, restored image. With an eye towards the Rubin Observatory, we analyze 4K by 4K Hyper Suprime-Cam exposures and obtain preliminary results which yield promising restored images and extracted source lists.