Astronomical image denoising by self-supervised deep learning and restoration processes

Abstract

Image denoising based on deep learning has witnessed significant advancements in recent years. However, existing deep learning methods lack quantitative control of the deviation or error on denoised images. The neural networks Self2Self is designed for denoising single-image, training on it and denoising itself, during which training is costly. In this work we explore training Self2Self on an astronomical image and denoising other images of the same kind, which is suitable for quickly denoising massive images in astronomy. To address the deviation issue, the abnormal pixels whose deviation exceeds a predefined threshold are restored to their initial values. The noise reduction includes training, denoising, restoring and named TDR-method, by which the noise level of the solar magnetograms is improved from about 8 G to 2 G. Furthermore, the TDR-method is applied to galaxy images from the Hubble Space Telescope and makes weak galaxy structures become much clearer. This capability of enhancing weak signals makes the TDR-method applicable in various disciplines.

Nature Astronomy online publication https://www.nature.com/articles/s41550-025-02484-z

References in corpus (11)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Noise2Noise: Learning Image Restoration without Clean Data
• The Hubble Ultra Deep Field
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• The Milky Way Imaging Scroll Painting (MWISP): Project Details and Initial Results from the Galactic Longitude of 25.8deg to 49.7deg
• Three-dimensional Magnetohydrodynamic Simulation of the Formation of Solar Chromospheric Jets with Twisted Magnetic Field Lines
• Mid-Infrared Imaging of Active Galaxies: Active Nuclei and Embedded Star Clusters
• Learning to Denoise Astronomical Images with U-nets
• Imaging the Circumnuclear Region of NGC 1365 with Chandra
• Solar image denoising with convolutional neural networks
• The Nuclear Region of NGC1365: Star Formation, Negative Feedback, and Outflow Structure

Cited by in corpus (2)

• Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising
• Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation