Learning Maximally Monotone Operators for Image Recovery

DOI10.1137/20M1387961zbMath1479.47058arXiv2012.13247OpenAlexW3118064383MaRDI QIDQ5860360

Audrey Repetti, Y. Wiaux, Matthieu Terris, Jean-Christophe Pesquet

Publication date: 19 November 2021

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2012.13247

zbMATH Keywords

convex optimizationneural networksinverse problemsmonotone operatorsnonlinear approximationcomputational imagingplug-and-play methods

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Convex programming (90C25) Numerical optimization and variational techniques (65K10) Computing methodologies for image processing (68U10) Monotone operators and generalizations (47H05) Approximation methods and heuristics in mathematical programming (90C59) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Nonlinear ill-posed problems (47J06) Decomposition methods (49M27)

Related Items (9)

Speckle reduction in matrix-log domain for synthetic aperture radar imaging ⋮ Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie ⋮ Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior ⋮ An Unrolled Implicit Regularization Network for Joint Image and Sensitivity Estimation in Parallel MR Imaging with Convergence Guarantee ⋮ Image Denoising: The Deep Learning Revolution and Beyond—A Survey Paper ⋮ Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems ⋮ Invertible residual networks in the context of regularization theory for linear inverse problems ⋮ On maximum a posteriori estimation with Plug \& Play priors and stochastic gradient descent ⋮ Convergence Results for Primal-Dual Algorithms in the Presence of Adjoint Mismatch

Uses Software

• UNLocBoX
• BSDS
• ImageNet
• Adam
• DnCNN
• ISTA-Net
• Wasserstein GAN

Cites Work

• Unnamed Item
• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• A primal-dual splitting method for convex optimization involving Lipschitzian, proximable and linear composite terms
• Monotone operator theory in convex optimization
• Multilayer feedforward networks are universal approximators
• A splitting algorithm for dual monotone inclusions involving cocoercive operators
• Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning
• Deep neural network structures solving variational inequalities
• Linear and nonlinear programming
• Characterization of the subdifferentials of convex functions
• Proximal Splitting Methods in Signal Processing
• Convergence Rates in Forward--Backward Splitting
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators
• Collaborative Filtering of Correlated Noise: Exact Transform-Domain Variance for Improved Shrinkage and Patch Matching
• Data-Driven Nonsmooth Optimization
• Deep unfolding of a proximal interior point method for image restoration
• Signal Recovery by Proximal Forward-Backward Splitting
• Proximité et dualité dans un espace hilbertien
• Total Generalized Variation
• Convex analysis and monotone operator theory in Hilbert spaces

This page was built for publication: Learning Maximally Monotone Operators for Image Recovery