Enregistré dans:
Détails bibliographiques
Auteurs principaux: Qu, Gang, Wang, Ping, Zheng, Siming, Yuan, Xin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.09528
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913988045963264
author Qu, Gang
Wang, Ping
Zheng, Siming
Yuan, Xin
author_facet Qu, Gang
Wang, Ping
Zheng, Siming
Yuan, Xin
contents Deep networks have achieved remarkable success in image compressed sensing (CS) task, namely reconstructing a high-fidelity image from its compressed measurement. However, existing works are deficient inincoherent compressed measurement at sensing phase and implicit measurement representations at reconstruction phase, limiting the overall performance. In this work, we answer two questions: 1) how to improve the measurement incoherence for decreasing the ill-posedness; 2) how to learn informative representations from measurements. To this end, we propose a novel asymmetric Kronecker CS (AKCS) model and theoretically present its better incoherence than previous Kronecker CS with minimal complexity increase. Moreover, we reveal that the unfolding networks' superiority over non-unfolding ones result from sufficient gradient descents, called explicit measurement representations. We propose a measurement-aware cross attention (MACA) mechanism to learn implicit measurement representations. We integrate AKCS and MACA into widely-used unfolding architecture to get a measurement-enhanced unfolding network (MEUNet). Extensive experiences demonstrate that our MEUNet achieves state-of-the-art performance in reconstruction accuracy and inference speed.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09528
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physics-guided Deep Unfolding Network for Enhanced Kronecker Compressive sensing
Qu, Gang
Wang, Ping
Zheng, Siming
Yuan, Xin
Computer Vision and Pattern Recognition
Deep networks have achieved remarkable success in image compressed sensing (CS) task, namely reconstructing a high-fidelity image from its compressed measurement. However, existing works are deficient inincoherent compressed measurement at sensing phase and implicit measurement representations at reconstruction phase, limiting the overall performance. In this work, we answer two questions: 1) how to improve the measurement incoherence for decreasing the ill-posedness; 2) how to learn informative representations from measurements. To this end, we propose a novel asymmetric Kronecker CS (AKCS) model and theoretically present its better incoherence than previous Kronecker CS with minimal complexity increase. Moreover, we reveal that the unfolding networks' superiority over non-unfolding ones result from sufficient gradient descents, called explicit measurement representations. We propose a measurement-aware cross attention (MACA) mechanism to learn implicit measurement representations. We integrate AKCS and MACA into widely-used unfolding architecture to get a measurement-enhanced unfolding network (MEUNet). Extensive experiences demonstrate that our MEUNet achieves state-of-the-art performance in reconstruction accuracy and inference speed.
title Physics-guided Deep Unfolding Network for Enhanced Kronecker Compressive sensing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.09528