paper-with-me

Papers

Learned convex regularizers for inverse problems

2020-08-06 · Subhadip Mukherjee, Sören Dittmer, Zakhar Shumaylov, Sebastian Lunz, Ozan Öktem, Carola-Bibiane Schönlieb

We consider the variational reconstruction framework for inverse problems and propose to learn a data-adaptive input-convex neural network (ICNN) as the regularization functional. The ICNN-based convex regularizer is trained adversarially to discern ground-truth images from unregularized reconstructions. Convexity of the regularizer is desirable since (i) one can establish analytical convergence guarantees for the corresponding variational reconstruction problem and (ii) devise efficient and provable algorithms for reconstruction. In particular, we show that the optimal solution to the variational problem converges to the ground-truth if the penalty parameter decays sub-linearly with respect to the norm of the noise. Further, we prove the existence of a sub-gradient-based algorithm that leads to a monotonically decreasing error in the parameter space with iterations. To demonstrate the performance of our approach for solving inverse problems, we consider the tasks of deblurring natural images and reconstructing images in computed tomography (CT), and show that the proposed convex regularizer is at least competitive with and sometimes superior to state-of-the-art data-driven techniques for inverse problems.

📄 PDF Abstract BibTeX arXiv:2008.02839

Code (1)

Subhadip-1/data_driven_convex_regularization pytorch

Tasks

Computed Tomography (CT)Deblurring

Similar Papers 제목 키워드 기반

Learning Difference-of-Convex Regularizers for Inverse Problems: A Flexible Framework with Theoretical Guarantees

2025-02-01 · Yasi Zhang, Oscar Leong

Learning effective regularization is crucial for solving ill-posed inverse problems, which arise in a wide range of scientific and engineering applications. While data-driven methods that parameterize regularizers using …

Computed Tomography (CT)CT Reconstruction

Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithms

2023-08-21 · Alexis Goujon, Sebastian Neumayer, Michael Unser

We propose to learn non-convex regularizers with a prescribed upper bound on their weak-convexity modulus. Such regularizers give rise to variational denoisers that minimize a convex energy. They rely on few parameters (…

Image ReconstructionMRI Reconstruction

MAP Image Recovery with Guarantees using Locally Convex Multi-Scale Energy (LC-MUSE) Model

2025-02-05 · Jyothi Rikhab Chand, Mathews Jacob

We propose a multi-scale deep energy model that is strongly convex in the local neighbourhood around the data manifold to represent its probability density, with application in inverse problems. In particular, we represe…

Image Reconstruction

Learning convex regularizers satisfying the variational source condition for inverse problems

2021-10-24 · NeurIPS Workshop Deep_Invers 2021 12 · Subhadip Mukherjee, Carola-Bibiane Schönlieb, Martin Burger

Variational regularization has remained one of the most successful approaches for reconstruction in imaging inverse problems for several decades. With the emergence and astonishing success of deep learning in recent year…

Learning Affine-Equivariant Proximal Operators

2026-04-16 · Oriel Savir, Zhenghan Fang, Jeremias Sulam arxiv

Proximal operators are fundamental across many applications in signal processing and machine learning, including solving ill-posed inverse problems. Recent work has introduced Learned Proximal Networks (LPNs), providing …