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

2026-04-17

AI Summary

Traditional radio interferometric imaging methods are constrained to reconstruction within a single domain—either visibility or image space—limiting their ability to exploit complementary information across domains and thereby compromising image quality. This work proposes CDCRec, a hierarchical multi-task, multi-stage framework that introduces an innovative self-supervised complementary modeling strategy to explicitly model and optimize cross-domain consistency between visibility and image domains. By integrating multi-modal data and leveraging self-supervised learning guided by cross-domain consistency constraints, CDCRec effectively overcomes the information bottleneck inherent in single-domain approaches. Experimental results demonstrate that CDCRec significantly outperforms existing methods under sparse observational conditions, achieving more accurate recovery of dense structures and substantially enhancing overall imaging performance.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health

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.

Problem

• radio interferometry
• image reconstruction
• cross-domain consistency
• visibility data
• dirty image

Innovation

• cross-domain consistency
• multimodal reconstruction
• radio interferometry
• self-supervised learning
• hierarchical multi-task framework