Compressive Sensing Reconstruction

Kan Chang, Pak Lun Kevin Ding, and Baoxin Li, “Compressive Sensing Reconstruction of Correlated Images Using Joint Regularization,”  IEEE Signal Processing Letters (SPL), vol.23, no.4, pp.449-453, Apr. 2016.

Compressive Sensing Reconstruction of Correlated Images Using Joint Regularization

Kan Chang, Pak Lun Kevin Ding, Baoxin Li

Abstract

This letter proposes a novel compressive sensing reconstruction method for correlated images by using joint regularization,

where a compensation-based adaptive total variation (CATV) regularization and a multi-image nonlocal low-rank

(MNLR) regularization are included. In CATV, local weights are assigned to the residual values in the gradient domain so as to

constrain the regularization strength at each pixel. In MNLR, the search of similar patches goes across different images so that both

self-similarity and inter-image similarity are explored. Afterward, an efficient algorithm is proposed to solve the joint formulation,

using a Split-Bregman-based technique. The effectiveness of the proposed approach is demonstrated with experiments on both

multiview images and video sequences.

Index Terms—Compressive sensing, motion estimation/disparity estimation (ME/DE), nonlocal low-rank regularization (NLR), total variation.

Source Code

To facilitate further evaluation and exploration of the method proposed in the above paper, we publish the source code at this link.

You are free to use the source code provided that (1) you clearly cite the source; and (2) you do not make any redistribution of the code.