1. Nonlocal Low-Rank Regularization Combined with Bilateral Total Variation for Compressive Sensing Image Reconstruction
- Author
-
Yingtian Hu, Kunhao Zhang, Huan Zheng, Hongliang Ren, and Yali Qin
- Subjects
bilateral total variation ,Rank (linear algebra) ,Computer Networks and Communications ,Computer science ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,compressive sensing ,lcsh:TK7800-8360 ,02 engineering and technology ,Iterative reconstruction ,01 natural sciences ,Regularization (mathematics) ,computational imaging ,Image (mathematics) ,010309 optics ,Computational photography ,0103 physical sciences ,0202 electrical engineering, electronic engineering, information engineering ,nonlocal self-similarity ,Electrical and Electronic Engineering ,Noise (signal processing) ,lcsh:Electronics ,Total variation denoising ,Compressed sensing ,Hardware and Architecture ,Control and Systems Engineering ,Computer Science::Computer Vision and Pattern Recognition ,Signal Processing ,Convex optimization ,020201 artificial intelligence & image processing ,weighted nuclear norm ,Algorithm - Abstract
The use of non-local self-similarity prior between image blocks can improve image reconstruction performance significantly. We propose a compressive sensing image reconstruction algorithm that combines bilateral total variation and nonlocal low-rank regularization to overcome over-smoothing and degradation of edge information which result from the prior reconstructed image. The proposed algorithm makes use of the preservation of image edge information by bilateral total variation operator to enhance the edge details of the reconstructed image. In addition, we use weighted nuclear norm regularization as a low-rank constraint for similar blocks of the image. To solve this convex optimization problem, the Alternating Direction Method of Multipliers (ADMM) is employed to optimize and iterate the algorithm model effectively. Experimental results show that the proposed algorithm can obtain better image reconstruction quality than conventional algorithms with using total variation regularization or considering the nonlocal structure of the image only. At 10% sampling rate, the peak signal-to-noise ratio gain is up to 2.39 dB in noiseless measurements compared with Nonlocal Low-rank Regularization (NLR-CS). Reconstructed image comparison shows that the proposed algorithm retains more high frequency components. In noisy measurements, the proposed algorithm is robust to noise and the reconstructed image retains more detail information.
- Published
- 2021