Journal of Imaging (Jun 2022)

Extra Proximal-Gradient Network with Learned Regularization for Image Compressive Sensing Reconstruction

  • Qingchao Zhang,
  • Xiaojing Ye,
  • Yunmei Chen

DOI
https://doi.org/10.3390/jimaging8070178
Journal volume & issue
Vol. 8, no. 7
p. 178

Abstract

Read online

Learned optimization algorithms are promising approaches to inverse problems by leveraging advanced numerical optimization schemes and deep neural network techniques in machine learning. In this paper, we propose a novel deep neural network architecture imitating an extra proximal gradient algorithm to solve a general class of inverse problems with a focus on applications in image reconstruction. The proposed network features learned regularization that incorporates adaptive sparsification mappings, robust shrinkage selections, and nonlocal operators to improve solution quality. Numerical results demonstrate the improved efficiency and accuracy of the proposed network over several state-of-the-art methods on a variety of test problems.

Keywords