SPAINANov 28, 2023

Deep Regularized Compound Gaussian Network for Solving Linear Inverse Problems

arXiv:2311.17248v34 citationsh-index: 11
Originality Incremental advance
AI Analysis

This work addresses robust signal and image reconstruction for applications like medical imaging, though it is incremental as it builds on prior regularization techniques.

The paper tackled linear inverse problems by developing a deep regularized neural network (DR-CG-Net) that learns prior information from the compound Gaussian class, showing it outperforms existing methods in tomographic imaging and compressive sensing, particularly in low-training scenarios.

Incorporating prior information into inverse problems, e.g. via maximum-a-posteriori estimation, is an important technique for facilitating robust inverse problem solutions. In this paper, we devise two novel approaches for linear inverse problems that permit problem-specific statistical prior selections within the compound Gaussian (CG) class of distributions. The CG class subsumes many commonly used priors in signal and image reconstruction methods including those of sparsity-based approaches. The first method developed is an iterative algorithm, called generalized compound Gaussian least squares (G-CG-LS), that minimizes a regularized least squares objective function where the regularization enforces a CG prior. G-CG-LS is then unrolled, or unfolded, to furnish our second method, which is a novel deep regularized (DR) neural network, called DR-CG-Net, that learns the prior information. A detailed computational theory on convergence properties of G-CG-LS and thorough numerical experiments for DR-CG-Net are provided. Due to the comprehensive nature of the CG prior, these experiments show that DR-CG-Net outperforms competitive prior art methods in tomographic imaging and compressive sensing, especially in challenging low-training scenarios.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes