Error Estimates for Data-driven Weakly Convex Frame-based Image Regularization

TL;DR

This paper introduces a learning-based, weakly convex regularization method for inverse problems like CT imaging, providing stability and convergence guarantees despite relaxing traditional non-expansiveness conditions.

Contribution

It proposes a novel non-linear filtered diagonal frame decomposition approach with learned filters, extending regularization theory to weakly convex settings for improved image reconstruction.

Findings

Learned filters are strictly increasing but not non-expansive.

Stability and convergence are established for the weakly convex regularizer.

Numerical experiments show improved reconstruction accuracy.

Abstract

Inverse problems are fundamental in fields like medical imaging, geophysics, and computerized tomography, aiming to recover unknown quantities from observed data. However, these problems often lack stability due to noise and ill-conditioning, leading to inaccurate reconstructions. To mitigate these issues, regularization methods are employed, introducing constraints to stabilize the inversion process and achieve a meaningful solution. Recent research has shown that the application of regularizing filters to diagonal frame decompositions (DFD) yields regularization methods. These filters dampen some frame coefficients to prevent noise amplification. This paper introduces a non-linear filtered DFD method combined with a learning strategy for determining optimal non-linear filters from training data pairs. In our experiments, we applied this approach to the inversion of the Radon transform using 500 image-sinogram pairs from real CT scans. Although the learned filters were found to be strictly increasing, they did not satisfy the non-expansiveness condition required to link them with convex regularizers and prove stability and convergence in the sense of regularization methods in previous works. Inspired by this, the paper relaxes the non-expansiveness condition, resulting in weakly convex regularization. Despite this relaxation, we managed to derive stability, convergence, and convergence rates with respect to the absolute symmetric Bregman distance for the learned non-linear regularizing filters. Extensive numerical results demonstrate the effectiveness of the proposed method in achieving stable and accurate reconstructions.