Edge adaptive hybrid regularization model for image deblurring

DOI10.1088/1361-6420/AC60BFzbMATH Open1489.94022arXiv2011.10260OpenAlexW3109942740MaRDI QIDQ5076009FDOQ5076009

Caiying Wu, Tieyong Zeng, Jie Chen, Ting-Ting Zhang, Zhifei He, Qiyu Jin

Publication date: 12 May 2022

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

Abstract: The parameter selection is crucial to regularization based image restoration methods. Generally speaking, a spatially fixed parameter for regularization item in the whole image does not perform well for both edge and smooth areas. A larger parameter of regularization item reduces noise better in smooth areas but blurs edge regions, while a small parameter sharpens edge but causes residual noise. In this paper, an automated spatially adaptive regularization model, which combines the harmonic and TV models, is proposed for reconstruction of noisy and blurred images. In the proposed model, it detects the edges and then spatially adjusts the parameters of Tikhonov and TV regularization terms for each pixel according to the edge information. Accordingly, the edge information matrix will be also dynamically updated during the iterations. Computationally, the newly-established model is convex, which can be solved by the semi-proximal alternating direction method of multipliers (sPADMM) with a linear-rate convergence rate. Numerical simulation results demonstrate that the proposed model effectively reserves the image edges and eliminates the noise and blur at the same time. In comparison to state-of-the-art algorithms, it outperforms other methods in terms of PSNR, SSIM and visual quality.

Full work available at URL: https://arxiv.org/abs/2011.10260

zbMATH Keywords

total variationimage deblurringsemi-proximal alternating direction method of multipliersedge information matrix

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Cites Work

• A New Alternating Minimization Algorithm for Total Variation Image Reconstruction
• Nonlinear total variation based noise removal algorithms
• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• Hankel matrix rank minimization with applications to system identification and realization
• The Split Bregman Method for L1-Regularized Problems
• An algorithm for total variation minimization and applications
• Noise removal using fourth-order partial differential equation with applications to medical magnetic resonance images in space and time
• Split Bregman Methods and Frame Based Image Restoration
• Augmented Lagrangian Method, Dual Methods, and Split Bregman Iteration for ROF, Vectorial TV, and High Order Models
• Image Restoration with Mixed or Unknown Noises
• Image restoration: Total variation, wavelet frames, and beyond
• Two-phase approach for deblurring images corrupted by impulse plus Gaussian noise
• Analysis of bounded variation penalty methods for ill-posed problems
• A Fast Total Variation Minimization Method for Image Restoration
• The Perona--Malik Paradox
• Automated regularization parameter selection in multi-scale total variation models for image restoration
• Linearized Bregman Iterations for Frame-Based Image Deblurring
• A multi-scale vectorial \(L^{\tau }\)-TV framework for color image restoration
• Low rank prior and total variation regularization for image deblurring
• A TV based restoration model with local constraints
• Regularizing properties of the Mumford–Shah functional for imaging applications
• A majorized ADMM with indefinite proximal terms for linearly constrained convex composite optimization
• A Weighted Difference of Anisotropic and Isotropic Total Variation Model for Image Processing
• Nonstationary iterated thresholding algorithms for image deblurring
• TV based image restoration with local constraints
• Image denoising by nonlinear nonlocal diffusion equations
• The study of an iterative method for the reconstruction of images corrupted by Poisson and Gaussian noise
• A Semiblind Regularization Algorithm for Inverse Problems with Application to Image Deblurring
• $ \newcommand{\e}{{\rm e}} \ell_{0}$ -minimization methods for image restoration problems based on wavelet frames
• Linear Rate Convergence of the Alternating Direction Method of Multipliers for Convex Composite Programming
• Deep unfolding of a proximal interior point method for image restoration
• Analytical aspects of spatially adapted total variation regularisation
• Simultaneous image fusion and denoising by using fractional-order gradient information
• A general truncated regularization framework for contrast-preserving variational signal and image restoration: motivation and implementation
• A linear systems approach to imaging through turbulence
• Nonconvex-TV Based Image Restoration with Impulse Noise Removal
• An edge preserving high-order PDE for multiframe image super-resolution
• An image sharpening operator combined with framelet for image deblurring
• The Maximum Entropy on the Mean Method for Image Deblurring
• An inner–outer iterative method for edge preservation in image restoration and reconstruction ^*
• An algorithm for total variation regularized photoacoustic imaging

Cited In (7)

• 3D Poissonian image deblurring via patch-based tensor logarithmic Schatten-\(p\) minimization
• Edge-Based Defocus Blur Estimation With Adaptive Scale Selection
• Adaptive total variational regularization of Gaussian denoisers for multiplicative noise removal
• Edge Modeling by Two Blur Parameters in Varying Contrasts
• Single image blind deblurring based on salient edge-structures and elastic-net regularization
• The optimal weights of non-local means for variance stabilized noise removal
• Bayesian inversion with Student's \(t\) priors based on Gaussian scale mixtures

This page was built for publication: Edge adaptive hybrid regularization model for image deblurring

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5076009)