Improving Radio Interferometry Imaging by Explicitly Modeling Cross-Domain Consistency in Reconstruction

arXiv cs.CV / 4/21/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper addresses limitations of radio interferometry reconstruction methods that treat the image (“dirty image”) and visibility (measured signals) domains independently.
It proposes CDCRec, a multimodal reconstruction approach that explicitly models cross-domain consistency to better capture mutual dependencies between the visibility and image domains.
The method uses a hierarchical multi-task, multi-stage framework to improve how interactions between the two domains are learned during reconstruction.
Experimental results show CDCRec delivers better imaging performance by extracting stronger cross-domain correlations, outperforming prior techniques that rely heavily on dense recovery from constrained source-domain data.
The authors emphasize a self-supervised complementary modeling strategy that improves interferometric domain translation where data is limited or constrained.

Abstract

Radio astronomy plays a crucial role in understanding the universe, particularly within the realm of non-thermal astrophysics. Images of celestial objects are derived from the signals (called visibility) measured by radio telescopes. Such imaging results, called dirty images, contain artifacts due to factors such as sparsity and therefore require reconstruction to improve imaging quality. Existing methods typically restrict reconstruction to a unimodal domain, either to the dirty image after imaging or to the sparse visibility prior to imaging. Focusing solely on each unimodal reconstruction results in the loss of complementary in-context information in either the visibility or image domain, leading to an incomplete modeling of mutual dependency and consistency. To address these challenges, we propose CDCRec, a multimodal radio interferometric data reconstruction method that explicitly models cross-domain consistency. We design a hierarchical multi-task and multi-stage framework to enhance the exploration of interplays between domains during reconstruction. Our experimental results demonstrate that CDCRec improves imaging performance through enhanced cross-domain correlation extraction. In particular, our self-supervised complementary modeling strategy is better than current methods at interferometric domain translations that rely heavily on recovering dense information from constrained source-domain data.