Work

Radio-Interferometric Image Reconstruction with Denoising Diffusion Restoration Models

Year: 2026

Type: preprint

Abstract: Reconstructing images of the radio sky from incomplete Fourier information is a key challenge in radio astronomy. In this work, we present a method for radio interferometric image reconstruction using a data-driven prior for the radio sky based on denoising diffusion probabilistic models (DDPMs). We train a DDPM on radio galaxy observations from the VLA FIRST survey, then create simulated VLBA, EHT, and ALMA observations of radio galaxies. We use an unsupervised posterior sampling method called Denoising Diffusion Restoration Models (DDRM) to reconstruct the corresponding images using our DDPM as a prior. Our approach naturally incorporates the PSF of the instrument. We are able to reconstruct images with very high fidelity and demonstrate a marked improvement over CLEAN and MS CLEAN. While DDRM naturally produces multiple samples, these are not calibrated and do not constitute reliable uncertainty estimates in the current implementation. The code for training and inference of the model is available at https://github.com/epfl-radio-astro/diffusionRI.git

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2601.15844

Authors: Morales, Michel, Tolley, Emma, Poitevineau, Remi

Institution: École Polytechnique Fédérale de Lausanne

Topic: Radio Astronomy Observations and Technology

Subfield: Astronomy and Astrophysics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: green

Funders: Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Centro Svizzero di Calcolo Scientifico, National Supercomputing Centre Singapore

Awards: Deep Waves: Accelerating Wave Dark Matter simulations with physics-informed deep learning & constraining Wave Dark Matter models with MeerKAT deep HI surveys, RadioClusters on the road to the SKA

OpenAlex ID: W7125489563

Cites:

Cited by:

Related to: