Skip to content
Open access

Data-Driven Regularization with Weak Convexity for Robust Image Reconstruction

Aug 2026 · SIAM Review · Vol 68, pp. 611-634 · 0 citations · 25 references
Computer Science

TL;DR

Overall, this framework shows that a controlled relaxation of convexity enables the design of learnable priors that achieve strong empirical performance while preserving mathematical guarantees.

Abstract

Abstract. We describe a practical framework for data-driven regularization in image reconstruction. It combines model expressivity with the guarantees of variational methods. The approach is based on a weakly convex ridge regularizer, defined as the composition of a convolutional filter bank and pointwise potentials constrained to be weakly convex. These potentials are implemented as learnable splines with a strict control of their weak-convexity modulus. The resulting denoisers outperform classic convex regularization techniques as well as competitive benchmarks such as BM3D, while they still correspond to the minimization of a convex energy. The learned regularizers further extend to general inverse problems with provable convergence to critical points. Overall, this framework shows that a controlled relaxation of convexity enables the design of learnable priors that achieve strong empirical performance while preserving mathematical guarantees.

Read PDF

Similar papers

Oct 2026

Accelerated stochastic iterative algorithms for image reconstruction via enhanced Regularization-by-Denoising

Inverse imaging problems such as denoising and deblurring aim to recover a clean image from corrupted measurements by incorporating prior knowledge. Classical regularizers like Tikhonov and total variation are mathematically convenient, yet they often oversimplify the complex structure of natural images. Regularization...

Yasmine El Mobariki, Brahim Khaider, Amine Laghrib et al. · 0 citations
Oct 2026

Image Restoration with Multiplicative Noise: A Hybrid Geometric Model and Its Alternating Minimization Algorithm

A hybrid regularization is introduced that combines these two complementary quantities to mitigate their respective drawbacks and provides a balanced control over both area and curvature, thereby preserving the advantages of each component.

Sheng-Kun Yang, Zhi-Chang Guo, Yao Li et al. · 1 citation
Open access 2026

Projection and Proximal Operators in Image Denoising

Image denoising is a classical inverse problem in which the recovery of a clean image from its noisy observation is complicated by ill-posedness. This paper develops a functional-analytic framework in which a broad class of denoising methods is expressed as the iteration of firmly nonexpansive or quasi-nonexpansive ope...

Inemesit D. Edem, D. Goodhead, Utomobong M. Okon · 0 citations

Principled MAP estimation for inverse problems: bridging the gap between convergence and performance

This paper designs an algorithm that combines denoisers at decreasing noise levels with a schedule tailored to ensure convergence, and proves that it surpasses convergent methods while competing with state-of-the-art empirical ones.

Alexandre Lagier, Valentine Tosel, Anne Gagneux et al. · 0 citations
Preprint Sep 2026

Accelerated Plug-and-Play Davis-Yin Splitting for Nonconvex Image Reconstruction

In this work, we study a class of structured non-convex and non-smooth optimization problems arising in imaging applications, where the objective is the sum of three functions. We consider the Davis-Yin splitting method, a FISTA-type accelerated variant, along with a quasi-Newton line-search method and a plug-and-play...

Kuntal Roy, Pankaj Gautam · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.