Restoration of Poissonian Images Using Alternating Direction Optimization

DOI10.1109/TIP.2010.2053941zbMATH Open1371.94128DBLPjournals/tip/FigueiredoB10arXiv1001.2244WikidataQ51662059 ScholiaQ51662059MaRDI QIDQ5366596FDOQ5366596

Authors: Mário A. T. Figueiredo, José M. Bioucas-Dias 

Publication date: 9 October 2017

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

Abstract: Much research has been devoted to the problem of restoring Poissonian images, namely for medical and astronomical applications. However, the restoration of these images using state-of-the-art regularizers (such as those based on multiscale representations or total variation) is still an active research area, since the associated optimization problems are quite challenging. In this paper, we propose an approach to deconvolving Poissonian images, which is based on an alternating direction optimization method. The standard regularization (or maximum a posteriori) restoration criterion, which combines the Poisson log-likelihood with a (non-smooth) convex regularizer (log-prior), leads to hard optimization problems: the log-likelihood is non-quadratic and non-separable, the regularizer is non-smooth, and there is a non-negativity constraint. Using standard convex analysis tools, we present sufficient conditions for existence and uniqueness of solutions of these optimization problems, for several types of regularizers: total-variation, frame-based analysis, and frame-based synthesis. We attack these problems with an instance of the alternating direction method of multipliers (ADMM), which belongs to the family of augmented Lagrangian algorithms. We study sufficient conditions for convergence and show that these are satisfied, either under total-variation or frame-based (analysis and synthesis) regularization. The resulting algorithms are shown to outperform alternative state-of-the-art methods, both in terms of speed and restoration accuracy.

Full work available at URL: https://arxiv.org/abs/1001.2244

Recommendations

• An alternating extragradient method for total variation-based image restoration from Poisson data
• Frame-based Poisson image restoration using a proximal linearized alternating direction method
• Primal-dual algorithms for total variation based image restoration under Poisson noise
• Restoring Poissonian images by a combined first-order and second-order variation approach
• A convex approach for image restoration with exact Poisson-Gaussian likelihood
• Alternating Direction Method of Multipliers for Nonlinear Image Restoration Problems
• Accelerated alternating minimization algorithm for Poisson noisy image recovery
• Total variation restoration of images corrupted by Poisson noise with iterated conditional expectations
• Alternating direction method for the high-order total variation-based Poisson noise removal problem
• Restoration of Poissonian images using nonconvex regularizer with overlapping group sparsity

Mathematics Subject Classification ID

Convex programming (90C25) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10)

Cited In (78)

• 3D Poissonian image deblurring via patch-based tensor logarithmic Schatten-\(p\) minimization
• PET-MRI joint reconstruction by joint sparsity based tight frame regularization
• A three-stage variational image segmentation framework incorporating intensity inhomogeneity information
• A consistent and numerically efficient variable selection method for sparse Poisson regression with applications to learning and signal recovery
• A new stopping criterion for Eckstein and Bertsekas's generalized alternating direction method of multipliers
• On the Use of ADMM for Imaging Inverse Problems: the Pros and Cons of Matrix Inversions
• Iterative reweighted algorithm for non-convex Poissonian image restoration model
• Image segmentation via Fischer-Burmeister total variation and thresholding
• Proximal Splitting Algorithms for Convex Optimization: A Tour of Recent Advances, with New Twists
• Poissonian image restoration via the \(L_1/L_2\)-based minimization
• The regularization continuation method for optimization problems with nonlinear equality constraints
• Image Denoising: The Deep Learning Revolution and Beyond—A Survey Paper
• Patch-based image restoration using expectation propagation
• A symmetric inertial alternating direction method of multipliers for elliptic equation constrained optimization problem
• A hybrid alternating minimization algorithm for structured convex optimization problems with application in Poissonian image processing
• Deconvolution and denoising for confocal microscopy
• A reweighted \(\ell^2\) method for image restoration with Poisson and mixed Poisson-Gaussian noise
• Efficient Bayesian Computation for Low-Photon Imaging Problems
• Augmented Lagrangian method for total generalized variation based Poissonian image restoration
• A new total variation model for restoring blurred and speckle noisy images
• Adaptive total variation regularization based scheme for Poisson noise removal
• Deblurring Poisson noisy images by total variation with overlapping group sparsity
• A nested primal-dual FISTA-like scheme for composite convex optimization problems
• Variational image restoration and segmentation with Rician noise
• A hybrid optimization method for multiplicative noise and blur removal
• High-order total variation-based Poissonian image deconvolution with spatially adapted regularization parameter
• Alternating direction method for the high-order total variation-based Poisson noise removal problem
• Restoration of Poissonian images using nonconvex regularizer with overlapping group sparsity
• Multiplicative Noise Removal for Texture Images Based on Adaptive Anisotropic Fractional Diffusion Equations
• A combined higher order non-convex total variation with overlapping group sparsity for Poisson noise removal
• Scaling techniques for gradient projection-type methods in astronomical image deblurring
• Blind Poissonian image deblurring regularized by a denoiser constraint and deep image prior
• A novel sparsity reconstruction method from Poisson data for 3D bioluminescence tomography
• Inertial variable metric techniques for the inexact forward-backward algorithm
• Deconvolution under Poisson noise using exact data fidelity and synthesis or analysis sparsity priors
• An efficient nonconvex regularization for wavelet frame and total variation based image restoration
• A noise-robust online convolutional coding model and its applications to Poisson denoising and image fusion
• Multiplicative noise removal via combining total variation and wavelet frame
• Variational approach for restoring blurred images with Cauchy noise
• Image deblurring via total variation based structured sparse model selection
• Point process estimation with Mirror Prox algorithms
• The regularization continuation method with an adaptive time step control for linearly constrained optimization problems
• Nonconvex regularization for blurred images with Cauchy noise
• A fast algorithm for deconvolution and Poisson noise removal
• A nonstationary accelerating alternating direction method for frame-based Poissonian image deblurring
• Optimal Inversion of the Anscombe Transformation in Low-Count Poisson Image Denoising
• Sparse and low-rank matrix regularization for learning time-varying Markov networks
• An alternating structured trust region algorithm for separable optimization problems with nonconvex constraints
• Non-convex and non-smooth variational decomposition for image restoration
• A new efficient variational model for multiplicative noise removal
• Numerical methods for parameter estimation in Poisson data inversion
• Total variation-based phase retrieval for Poisson noise removal
• On Hamilton-Jacobi PDEs and image denoising models with certain nonadditive noise
• Color image restoration with mixed Gaussian-Cauchy noise and blur
• A nonlocal low rank model for Poisson noise removal
• A modified Chambolle-Pock primal-dual algorithm for Poisson noise removal
• Multiplicative noise removal: nonlocal low-rank model and its proximal alternating reweighted minimization algorithm
• Poisson noise reduction with non-local PCA
• An alternating direction method for total variation denoising
• Generalized ADMM with optimal indefinite proximal term for linearly constrained convex optimization
• Iterative reweighted total generalized variation based Poisson noise removal model
• Primal-dual algorithms for total variation based image restoration under Poisson noise
• Sampling-based uncertainty quantification in deconvolution of X-ray radiographs
• Image restoration using total variation with overlapping group sparsity
• Restoring Poissonian images by a combined first-order and second-order variation approach
• High-order total bounded variation model and its fast algorithm for Poissonian image restoration
• A Patch-Based Low-Rank Minimization Approach for Speckle Noise Reduction in Ultrasound Images
• Scaling techniques for \(\epsilon\)-subgradient methods
• Poisson Noise Reduction with Higher-Order Natural Image Prior Model
• A view of computational models for image segmentation
• An inexact alternating direction method of multipliers with relative error criteria
• Point-spread function identification in an image restoration problem
• Non-blind and blind deconvolution under Poisson noise using fractional-order total variation
• ACQUIRE: an inexact iteratively reweighted norm approach for TV-based Poisson image restoration
• Poisson image denoising based on fractional-order total variation
• Poissonian image deconvolution via sparse and redundant representations and framelet regularization
• Inexact Bregman iteration for deconvolution of superimposed extended and point sources
• A new nonconvex approach for image restoration with Gamma noise

This page was built for publication: Restoration of Poissonian Images Using Alternating Direction Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5366596)