Learning weakly convex regularizers for convergent image-reconstruction algorithms

DOI10.1137/23m1565243MaRDI QIDQ6541905

Sebastian Neumayer, Michael Unser, Alexis Goujon

Publication date: 21 May 2024

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

zbMATH Keywords

splinesinverse problemsdenoisingbilevel optimizationweak convexitydata-driven priors

Mathematics Subject Classification ID

Numerical computation using splines (65D07) Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies for image processing (68U10) Convexity of real functions of several variables, generalizations (26B25) Linear operators and ill-posed problems, regularization (47A52) Inverse problems in optimal control (49N45)

Cites Work

• Unnamed Item
• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• Parseval proximal neural networks
• Fields of experts
• Local convergence of the heavy-ball method and iPiano for non-convex optimization
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• A characterization of proximity operators
• Adaptive restart for accelerated gradient schemes
• First-order methods almost always avoid strict saddle points
• Adaptive wavelet thresholding for image denoising and compression
• Energy Minimization Methods
• iPiano: Inertial Proximal Algorithm for Nonconvex Optimization
• Insights Into Analysis Operator Learning: From Patch-Based Sparse Models to Higher Order MRFs
• De-noising by soft-thresholding
• NETT: solving inverse problems with deep neural networks
• Linearly involved generalized Moreau enhanced models and their proximal splitting algorithm under overall convexity condition
• Compressed sensing
• Approximation of Lipschitz Functions Using Deep Spline Neural Networks
• Sparsity-Inducing Nonconvex Nonseparable Regularization for Convex Image Processing

Related Items (1)

Iteratively Refined Image Reconstruction with Learned Attentive Regularizers

This page was built for publication: Learning weakly convex regularizers for convergent image-reconstruction algorithms