| |
 |
| Paper: |
Learning the Night Sky with Deep Generative Priors |
| Volume: |
538, ADASS XXXII |
| Page: |
198 |
| Authors: |
Fausto Navarro; Daniel Hall; Tamás Budavári; Yashil Sukurdeep |
| DOI: |
10.26624/GHBF1934 |
| Abstract: |
Recovering sharper images from blurred observations, referred to as de-convolution, 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. |
|
|
|
|
|
