CLEAR: covariant least-square refitting with applications to image restoration

DOI10.1137/16M1080318zbMATH Open1365.49034arXiv1606.05158OpenAlexW2593459174MaRDI QIDQ5266374FDOQ5266374

Authors: Charles-Alban Deledalle, Nicolas Papadakis, Joseph Salmon, Samuel Vaiter 

Publication date: 2 June 2017

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

Abstract: In this paper, we propose a new framework to remove parts of the systematic errors affecting popular restoration algorithms, with a special focus for image processing tasks. Generalizing ideas that emerged for $el{l}_1$ regularization, we develop an approach re-fitting the results of standard methods towards the input data. Total variation regularizations and non-local means are special cases of interest. We identify important covariant information that should be preserved by the re-fitting method, and emphasize the importance of preserving the Jacobian (w.r.t. the observed signal) of the original estimator. Then, we provide an approach that has a "twicing" flavor and allows re-fitting the restored signal by adding back a local affine transformation of the residual term. We illustrate the benefits of our method on numerical simulations for image restoration tasks.

Full work available at URL: https://arxiv.org/abs/1606.05158

Recommendations

• Total variation structured total least squares method for image restoration
• An Iterative Regularization Method for Total Variation-Based Image Restoration
• On debiasing restoration algorithms: applications to total-variation and nonlocal-means
• A new approach to constrained total least squares image restoration
• On removing blur in images using least squares solutions

zbMATH Keywords

boostinginverse problemsvariational methodsrefittingdebiasingtwicing

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Computing methodologies for image processing (68U10) Inverse problems in optimal control (49N45)

Cites Work

• Nonlinear total variation based noise removal algorithms
• Least angle regression. (With discussion)
• Ideal spatial adaptation by wavelet shrinkage
• Title not available (Why is that?)
• Local behavior of sparse analysis regularization: applications to risk estimation
• On the Numerical Solution of Heat Conduction Problems in Two and Three Space Variables
• Title not available (Why is that?)
• Model Selection and Estimation in Regression with Grouped Variables
• Ridge Regression: Biased Estimation for Nonorthogonal Problems
• Least squares after model selection in high-dimensional sparse models
• Title not available (Why is that?)
• On Measuring and Correcting the Effects of Data Mining and Model Selection
• Boosting With theL₂Loss
• Component selection and smoothing in multivariate nonparametric regression
• The Lasso problem and uniqueness
• Boosting of Image Denoising Algorithms
• Progressive Image Denoising
• How to SAIF-ly Boost Denoising Performance
• A Review of Image Denoising Algorithms, with a New One
• A first-order primal-dual algorithm for convex problems with applications to imaging
• Title not available (Why is that?)
• Evaluating Derivatives
• Edge-preserving and scale-dependent properties of total variation regularization
• Stein Unbiased GrAdient estimator of the Risk (SUGAR) for Multiple Parameter Selection
• An Iterative Regularization Method for Total Variation-Based Image Restoration
• Exponential screening and optimal rates of sparse estimation
• Iterative thresholding for sparse approximations
• Analysis versus synthesis in signal priors
• A bias-variance approach for the nonlocal means
• Support union recovery in high-dimensional multivariate regression
• A Total Variation Spectral Framework for Scale and Texture Analysis
• Nonlinear inverse scale space methods
• Title not available (Why is that?)
• Adaptive Model Selection
• Non-local methods with shape-adaptive patches (NLM-SAP)
• Minimax multiple shrinkage estimation
• Sparse recovery via differential inclusions
• Recursive bias estimation for multivariate regression smoothers
• Optimal Jacobian accumulation is NP-complete
• The degrees of freedom of partly smooth regularizers
• On Debiasing Restoration Algorithms: Applications to Total-Variation and Nonlocal-Means
• Nonlocal Means With Dimensionality Reduction and SURE-Based Parameter Selection
• Geometric properties of solutions to the total variation denoising problem

Cited In (13)

• A Convex Approach to Superresolution and Regularization of Lines in Images
• Unified models for second-order TV-type regularisation in imaging: a new perspective based on vector operators
• Bias reduction in variational regularization
• Recent approaches for image colorization
• Block-based refitting in \(\ell_{12}\) sparse regularization
• Contrast invariant SNR and isotonic regressions
• On Lasso refitting strategies
• Interactive Video Colorization Within a Variational Framework
• Adaptive anisotropic total variation: analysis and experimental findings of nonlinear spectral properties
• Variational regularization in inverse problems and machine learning
• Modern regularization methods for inverse problems
• Linear support vector regression with linear constraints
• An improved image denoising model based on nonlocal means filter

Uses Software

• ibr

This page was built for publication: CLEAR: covariant least-square refitting with applications to image restoration

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5266374)