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

arXiv: https://arxiv.org/abs/2604.16793 · HTML: https://mlsanity.com/paper/2604.16793/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 40 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Builds on (most cited first, 5 of 5)

- [Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising](https://mlsanity.com/paper/2602.17205/) (2026)
- [DAS-N2N: Machine learning Distributed Acoustic Sensing (DAS) signal denoising without clean data](https://mlsanity.com/paper/2304.08120/) (2023)
- [Radio-astronomical Image Reconstruction with Conditional Denoising Diffusion Model](https://mlsanity.com/paper/2402.10204/) (2024)
- [Solar image denoising with convolutional neural networks](https://mlsanity.com/paper/1908.02815/) (2019)
- [AstroClearNet: Deep image prior for multi-frame astronomical image restoration](https://mlsanity.com/paper/2504.06463/) (2025)

## Abstract (arXiv)

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.