A convex variational model for learning convolutional image atoms from incomplete data

DOI10.1007/s10851-019-00919-7zbMath1434.68625arXiv1812.03077OpenAlexW2989306638WikidataQ92000473 ScholiaQ92000473MaRDI QIDQ1988356

Yanyan Li

Publication date: 23 April 2020

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1812.03077

zbMATH Keywords

inverse problemsvariational methodsconvex relaxationmachine learningtexture reconstructionfunctional liftingconvolutional Lassolearning approaches

Mathematics Subject Classification ID

Ill-posedness and regularization problems in numerical linear algebra (65F22) Numerical methods involving duality (49M29) Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies for image processing (68U10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Optimality conditions for solutions belonging to restricted classes (Lipschitz controls, bang-bang controls, etc.) (49K30)

Related Items (8)

Regularization graphs—a unified framework for variational regularization of inverse problems ⋮ Deep Learning--Based Dictionary Learning and Tomographic Image Reconstruction ⋮ A Generative Variational Model for Inverse Problems in Imaging ⋮ A Note on the Regularity of Images Generated by Convolutional Neural Networks ⋮ A convex variational model for learning convolutional image atoms from incomplete data ⋮ convex_learning ⋮ Solving inverse problems using data-driven models ⋮ Overcomplete representation in a hierarchical Bayesian framework

Uses Software

• GitHub
• SPORCO
• BM3D
• DeepAdverserialRegulariser

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• Regularization of linear inverse problems with total generalized variation
• Variational methods in imaging
• Applied functional analysis. Functional analysis, Sobolev spaces and elliptic differential equations
• Singular value inequalities for matrix sums and minors
• Optimal selection of the regularization function in a weighted total variation model. I: Modelling and theory
• Convergence radius and sample complexity of ITKM algorithms for dictionary learning
• The convex geometry of linear inverse problems
• A first-order primal-dual algorithm for convex problems with applications to imaging
• A convex variational model for learning convolutional image atoms from incomplete data
• RNLp: mixing nonlocal and TV-Lp methods to remove impulse noise from images
• A TGV-Based Framework for Variational Image Decompression, Zooming, and Reconstruction. Part II: Numerics
• A Bilevel Optimization Approach for Parameter Learning in Variational Models
• Simultaneously Structured Models With Application to Sparse and Low-Rank Matrices
• Blind Deconvolution Using Convex Programming
• Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
• Secrets of image denoising cuisine
• Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems
• Regularization with non-convex separable constraints
• Bilevel approaches for learning of variational imaging models
• Coupled regularization with multiple data discrepancies
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning
• On Infimal Convolution of TV-Type Functionals and Applications to Video and Image Reconstruction
• Infimal Convolution of Oscillation Total Generalized Variation for the Recovery of Images with Structured Texture
• Regularized gradient descent: a non-convex recipe for fast joint blind deconvolution and demixing
• A convergence rates result for Tikhonov regularization in Banach spaces with non-smooth operators
• A Review of Image Denoising Algorithms, with a New One
• An introduction to continuous optimization for imaging
• Total Generalized Variation

This page was built for publication: A convex variational model for learning convolutional image atoms from incomplete data