Learning optimal spatially-dependent regularization parameters in total variation image denoising

DOI10.1088/1361-6420/33/7/074005zbMath1371.49018arXiv1603.09155OpenAlexW2963683570MaRDI QIDQ5348007

Carola-Bibiane Schönlieb, Juan Carlos De Los Reyes, Cao Van Chung

Publication date: 11 August 2017

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

Full work available at URL: https://arxiv.org/abs/1603.09155

zbMATH Keywords

Schwarz domain decompositionbilevel optimizationPDE-constrained optimizationsemismooth Newton methodoptimization-based learning in imaging

Mathematics Subject Classification ID

Optimality conditions for problems involving partial differential equations (49K20) Numerical optimization and variational techniques (65K10) Computing methodologies for image processing (68U10) Newton-type methods (49M15) Methods of quasi-Newton type (90C53) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Related Items

Locally adaptive total variation for removing mixed Gaussian–impulse noise ⋮ A high order PDE-constrained optimization for the image denoising problem ⋮ Optimality Conditions for Bilevel Imaging Learning Problems with Total Variation Regularization ⋮ Bilevel Training Schemes in Imaging for Total Variation--Type Functionals with Convex Integrands ⋮ Spatially adapted first and second order regularization for image reconstruction: from an image surface perspective ⋮ An improved bilevel optimization approach for image super-resolution based on a fractional diffusion tensor ⋮ Dualization and Automatic Distributed Parameter Selection of Total Generalized Variation via Bilevel Optimization ⋮ Preface for Inverse Problems special issue on learning and inverse problems ⋮ Bilevel Imaging Learning Problems as Mathematical Programs with Complementarity Constraints: Reformulation and Theory ⋮ Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling ⋮ On and Beyond Total Variation Regularization in Imaging: The Role of Space Variance ⋮ Parameter space study of optimal scale-dependent weights in TV image denoising ⋮ An adaptive finite element method for distributed elliptic optimal control problems with variable energy regularization ⋮ Structural changes in nonlocal denoising models arising through bi-level parameter learning ⋮ Deep Learning for Trivial Inverse Problems ⋮ Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach Part I: Methodology and Experiments ⋮ Automated parameter selection for total variation minimization in image restoration ⋮ Gradient-Based Solution Algorithms for a Class of Bilevel Optimization and Optimal Control Problems with a Nonsmooth Lower Level ⋮ Modern regularization methods for inverse problems ⋮ Solving inverse problems using data-driven models ⋮ An optimal bilevel optimization model for the generalized total variation and anisotropic tensor parameters selection

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Error estimates for optimal control problems of a class of quasilinear equations arising in variable viscosity fluid flow
• Optimization of mixed variational inequalities arising in flow of viscoplastic materials
• The structure of optimal parameters for image restoration problems
• A \(W^{1,p}\)-estimate for solutions to mixed boundary value problems for second order elliptic differential equations
• Automated regularization parameter selection in multi-scale total variation models for image restoration
• Statistical multiresolution Dantzig estimation in imaging: fundamental concepts and algorithmic framework
• Image denoising: learning the noise model via nonsmooth PDE-constrained optimization
• Statistical multiresolution estimation for variational imaging: with an application in Poisson-biophotonics
• Spatially dependent regularization parameter selection in total generalized variation models for image restoration
• A Bilevel Optimization Approach for Parameter Learning in Variational Models
• Shape-constrained regularization by statistical multiresolution for inverse problems: asymptotic analysis
• Numerical PDE-Constrained Optimization
• Bilevel Optimization with Nonsmooth Lower Level Problems
• Lagrange Multiplier Approach to Variational Problems and Applications
• The Primal-Dual Active Set Strategy as a Semismooth Newton Method
• A Multiscale Image Representation Using Hierarchical (BV,L²) Decompositions
• Computational Methods for Inverse Problems
• An Infeasible Primal-Dual Algorithm for Total Bounded Variation--Based Inf-Convolution-Type Image Restoration
• Optimized Schwarz Methods
• Scale Recognition, Regularization Parameter Selection, and Meyer's G Norm in Total Variation Regularization
• Two finite-difference schemes for calculation of Bingham fluid flows in a cavity