Image compressive sensing recovery via group residual based nonlocal low-rank regularization

• Published in: Neurocomputing (Amsterdam) 2021-08, Vol.449, p.315-329
• Main Authors: Xu, Jin, Fu, Zhizhong, Zhu, Xiaodong
• Format: Article
• Language: English
• Subjects: Image compressive sensing recovery; Nonlocal low-rank regularization; Residual of patch group; Split Bregman iteration; Weighted Schatten p-norm
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2021.03.101

To address the ill-posed nature of image compressive sensing (CS) recovery, it is of great importance to properly exploit image priors. In this paper, we propose a novel group residual based nonlocal low-rank regularization for image CS recovery, namely GRNLR-CS, which performs nonlocal low-rank modeling based on the residual of patch group rather than on the patch group itself as conventional methods. In our GRNLR-CS, the weighted Schatten p-norm is adopted as a non-convex surrogate function to estimate the rank of the group residual. To make our GRNLR-CS method tractable and robust, the split Bregman iteration technique is employed to develop an efficient algorithm to solve the optimization problem of GRNLR-CS. Extensive experimental results demonstrate that our GRNLR-CS method outperforms some state-of-the-art optimization based or deep learning based methods for image CS recovery.