Learning the Night Sky with Deep Generative Priors
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912627307839488 |
|---|---|
| author | Navarro, Fausto Hall, Daniel Budavari, Tamas Sukurdeep, Yashil |
| author_facet | Navarro, Fausto Hall, Daniel Budavari, Tamas Sukurdeep, Yashil |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_02030 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning the Night Sky with Deep Generative Priors Navarro, Fausto Hall, Daniel Budavari, Tamas Sukurdeep, Yashil Computer Vision and Pattern Recognition Instrumentation and Methods for Astrophysics Image and Video Processing 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. |
| title | Learning the Night Sky with Deep Generative Priors |
| topic | Computer Vision and Pattern Recognition Instrumentation and Methods for Astrophysics Image and Video Processing |
| url | https://arxiv.org/abs/2302.02030 |