AstroSURE: Learning to Remove Noise from Astronomical Images Without Ground Truth Data

TL;DR

This paper evaluates deep-learning denoising methods that do not require ground-truth images, demonstrating their effectiveness in improving faint-source detection in astronomical images from HST and CFHT.

Contribution

It adapts and compares several unsupervised denoising techniques for astronomical imaging, highlighting their potential and limitations across different telescopes.

Findings

Methods improve faint-source detectability over original images.

Domain similarity affects transferability of denoising models.

Encouraging gains observed on HST data after domain-specific initialization.

Abstract

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.