LR-CSNet: Low-Rank Deep Unfolding Network for Image Compressive Sensing

Tianfang Zhang, Lei Li, Christian Igel, Stefan Oehmcke, Fabian Gieseke, Zhenming Peng

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

7 Citations (Scopus)
13 Downloads (Pure)

Abstract

Deep unfolding networks (DUNs) have proven to be a viable approach to compressive sensing (CS). In this work, we propose a DUN called low-rank CS network (LR-CSNet) for natural image CS. Real-world image patches are often well-represented by low-rank approximations. LR-CSNet exploits this property by adding a low-rank prior to the CS optimization task. We derive a corresponding iterative optimization procedure using variable splitting, which is then translated to a new DUN architecture. The architecture uses low-rank generation modules (LRGMs), which learn low-rank matrix factorizations, as well as gradient descent and proximal mappings (GDPMs), which are proposed to extract high-frequency features to refine image details. In addition, the deep features generated at each reconstruction stage in the DUN are transferred between stages to boost the performance. Our extensive experiments on three widely considered datasets demonstrate the promising performance of LR-CSNet compared to state-of-the-art methods in natural image CS.
Original languageEnglish
Title of host publication2022 IEEE International Conference on Computer and Communications (ICCC), Chengdu, China
PublisherIEEE
Publication date2023
Pages1951-1957
DOIs
Publication statusPublished - 2023
EventInternational Conference on Computer and Communications -
Duration: 9 Dec 202212 Dec 2022
Conference number: 8
http://www.iccc.org/2022.html

Conference

ConferenceInternational Conference on Computer and Communications
Number8
Period09/12/202212/12/2022
Internet address

Cite this