Saved in:
Bibliographic Details
Main Authors: Vaheb, Omid, Fabbro, Sebastien, Draper, Stark
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.16793
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910143104417792
author Vaheb, Omid
Fabbro, Sebastien
Draper, Stark
author_facet Vaheb, Omid
Fabbro, Sebastien
Draper, Stark
contents In astronomical imaging, the low photon count of exposures necessitates extensive post-processing steps, including contamination removal and denoising. This paper evaluates deep-learning denoising methods that can be trained without clean ground-truth images and assesses their utility for detection11 oriented analysis of astronomical data. We adapt and compare Noise2Noise, Stein's Unbiased Risk Estimator, and blind-spot-based methods using synthetic data and real observations from the Hubble Space Telescope (HST) and the Canada-France-Hawaii Telescope (CFHT). Performance is evaluated using object-detection metrics, including correct detection rate and false alarm rate, together with image-based metrics and pixel-distribution diagnostics. The results show that these methods can improve faint-source detectability relative to the original noisy images, with encouraging gains on HST data after domain-consistent initialization, while transfer to CFHT data is more limited, highlighting the importance of instrument/domain similarity for unsupervised adaptation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16793
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AstroSURE: Learning to Remove Noise from Astronomical Images Without Ground Truth Data
Vaheb, Omid
Fabbro, Sebastien
Draper, Stark
Instrumentation and Methods for Astrophysics
Computer Vision and Pattern Recognition
In astronomical imaging, the low photon count of exposures necessitates extensive post-processing steps, including contamination removal and denoising. This paper evaluates deep-learning denoising methods that can be trained without clean ground-truth images and assesses their utility for detection11 oriented analysis of astronomical data. We adapt and compare Noise2Noise, Stein's Unbiased Risk Estimator, and blind-spot-based methods using synthetic data and real observations from the Hubble Space Telescope (HST) and the Canada-France-Hawaii Telescope (CFHT). Performance is evaluated using object-detection metrics, including correct detection rate and false alarm rate, together with image-based metrics and pixel-distribution diagnostics. The results show that these methods can improve faint-source detectability relative to the original noisy images, with encouraging gains on HST data after domain-consistent initialization, while transfer to CFHT data is more limited, highlighting the importance of instrument/domain similarity for unsupervised adaptation.
title AstroSURE: Learning to Remove Noise from Astronomical Images Without Ground Truth Data
topic Instrumentation and Methods for Astrophysics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.16793