DRIP: deep regularizers for inverse problems

DOI10.1088/1361-6420/AD0F3BarXiv2304.00015OpenAlexW4388934007MaRDI QIDQ6141552FDOQ6141552

Moshe Eliasof, Eldad Haber, Eran Treister

Publication date: 20 December 2023

Published in: Inverse Problems (Search for Journal in Brave)

Abstract: Inverse problems are mathematically ill-posed. Thus, given some (noisy) data, there is more than one solution that fits the data. In recent years, deep neural techniques that find the most appropriate solution, in the sense that it contains a-priori information, were developed. However, they suffer from several shortcomings. First, most techniques cannot guarantee that the solution fits the data at inference. Second, while the derivation of the techniques is inspired by the existence of a valid scalar regularization function, such techniques do not in practice rely on such a function, and therefore veer away from classical variational techniques. In this work we introduce a new family of neural regularizers for the solution of inverse problems. These regularizers are based on a variational formulation and are guaranteed to fit the data. We demonstrate their use on a number of highly ill-posed problems, from image deblurring to limited angle tomography.

Full work available at URL: https://arxiv.org/abs/2304.00015

zbMATH Keywords

inverse problemsvariational methodsproximal methodsdeep neural networks

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Artificial neural networks and deep learning (68T07) Computational aspects of data analysis and big data (68T09) Large-scale problems in mathematical programming (90C06) Computing methodologies for image processing (68U10) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20)

Cites Work

• Nonlinear total variation based noise removal algorithms
• Title not available (Why is that?)
• A distribution-free M-estimator of multivariate scatter
• Rank-Deficient and Discrete Ill-Posed Problems
• From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images
• For most large underdetermined systems of linear equations the minimal 𝓁₁‐norm solution is also the sparsest solution
• The mathematics of computerized tomography
• Convergence Results for a Coordinate Projection Method Applied to Mechanical Systems with Algebraic Constraints
• Title not available (Why is that?)
• Title not available (Why is that?)
• Statistical regularization of inverse problems
• Deblurring Images
• Nonstationary iterated Tikhonov regularization
• Nonlinear inverse scale space methods
• A multilevel framework for sparse optimization with application to inverse covariance estimation and logistic regression
• Learning regularization functionals a supervised training approach
• Data analysis tools for uncertainty quantification of inverse problems
• Deep neural networks motivated by partial differential equations
• Solving ill-posed inverse problems using iterative deep neural networks
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Learning regularization parameters of inverse problems via deep neural networks
• Data-consistent neural networks for solving nonlinear inverse problems
• Unsupervised knowledge-transfer for learned image reconstruction*

This page was built for publication: DRIP: deep regularizers for inverse problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6141552)