Group-Based Sparse Representation for Image Restoration

DOI10.1109/TIP.2014.2323127zbMATH Open1374.94445arXiv1405.3351WikidataQ50662126 ScholiaQ50662126MaRDI QIDQ4592369FDOQ4592369

Authors: Jian Zhang, Debin Zhao, Wen Gao 

Publication date: 20 November 2017

Published in: IEEE Transactions on Image Processing (Search for Journal in Brave)

Abstract: Traditional patch-based sparse representation modeling of natural images usually suffer from two problems. First, it has to solve a large-scale optimization problem with high computational complexity in dictionary learning. Second, each patch is considered independently in dictionary learning and sparse coding, which ignores the relationship among patches, resulting in inaccurate sparse coding coefficients. In this paper, instead of using patch as the basic unit of sparse representation, we exploit the concept of group as the basic unit of sparse representation, which is composed of nonlocal patches with similar structures, and establish a novel sparse representation modeling of natural images, called group-based sparse representation (GSR). The proposed GSR is able to sparsely represent natural images in the domain of group, which enforces the intrinsic local sparsity and nonlocal self-similarity of images simultaneously in a unified framework. Moreover, an effective self-adaptive dictionary learning method for each group with low complexity is designed, rather than dictionary learning from natural images. To make GSR tractable and robust, a split Bregman based technique is developed to solve the proposed GSR-driven minimization problem for image restoration efficiently. Extensive experiments on image inpainting, image deblurring and image compressive sensing recovery manifest that the proposed GSR modeling outperforms many current state-of-the-art schemes in both PSNR and visual perception.

Full work available at URL: https://arxiv.org/abs/1405.3351

Mathematics Subject Classification ID

Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Cited In (27)

• Image inpainting via modified exemplar-based inpainting with two-stage structure tensor and image sparse representation
• Nonconvex \(L_{1/2}\)-regularized nonlocal self-similarity denoiser for compressive sensing based CT reconstruction
• Cardinality minimization, constraints, and regularization: a survey
• A perturbation analysis based on group sparse representation with orthogonal matching pursuit
• Generative imaging and image processing via generative encoder
• A support-denoiser-driven framework for single image restoration
• Group sparse representation for restoring blurred images with Cauchy noise
• Recent development of dual-dictionary learning approach in medical image analysis and reconstruction
• Cauchy noise removal using group-based low-rank prior
• A Corrected Tensor Nuclear Norm Minimization Method for Noisy Low-Rank Tensor Completion
• Weighted \(l_p\) norm sparse error constraint based ADMM for image denoising
• Restoration guarantee of image inpainting via low rank patch matrix completion
• Truncated Nuclear Norm Minimization Based Group Sparse Representation for Image Restoration
• A weighted block dictionary learning algorithm for classification
• Nonlocal Cahn-Hilliard type model for image inpainting
• Two-stage image denoising via an enhanced low-rank prior
• Nonconvex nonsmooth low-rank minimization for generalized image compressed sensing via group sparse representation
• The rank residual constraint model with weighted Schatten \(p\)-norm minimization for image denoising
• Image restoration method based on fractional variable order differential
• A Ginzburg-Landau-\({H}^{-1}\) model and its SAV algorithm for image inpainting
• Blind image deblurring via the weighted Schatten \(p\)-norm minimization prior
• Group Sparse Optimization for Images Recovery Using Capped Folded Concave Functions
• Multiple-prespecified-dictionary sparse representation for compressive sensing image reconstruction with nonconvex regularization
• Semisupervised dictionary learning with graph regularized and active points
• Robust image compressive sensing based on half-quadratic function and weighted Schatten-\(p\) norm
• Autogrouped Sparse Representation for Visual Analysis
• Image inpainting using non-convex low rank decomposition and multidirectional search

This page was built for publication: Group-Based Sparse Representation for Image Restoration

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4592369)