The Little Engine that Could: Regularization by Denoising (RED)
From MaRDI portal
Abstract: Removal of noise from an image is an extensively studied problem in image processing. Indeed, the recent advent of sophisticated and highly effective denoising algorithms lead some to believe that existing methods are touching the ceiling in terms of noise removal performance. Can we leverage this impressive achievement to treat other tasks in image processing? Recent work has answered this question positively, in the form of the Plug-and-Play Prior () method, showing that any inverse problem can be handled by sequentially applying image denoising steps. This relies heavily on the ADMM optimization technique in order to obtain this chained denoising interpretation. Is this the only way in which tasks in image processing can exploit the image denoising engine? In this paper we provide an alternative, more powerful and more flexible framework for achieving the same goal. As opposed to the method, we offer Regularization by Denoising (RED): using the denoising engine in defining the regularization of the inverse problem. We propose an explicit image-adaptive Laplacian-based regularization functional, making the overall objective functional clearer and better defined. With a complete flexibility to choose the iterative optimization procedure for minimizing the above functional, RED is capable of incorporating any image denoising algorithm, treat general inverse problems very effectively, and is guaranteed to converge to the globally optimal result. We test this approach and demonstrate state-of-the-art results in the image deblurring and super-resolution problems.
Recommendations
- Regularization by denoising via fixed-point projection (RED-PRO)
- Noiseless regularisation by noise
- Regularization under general noise assumptions
- Regularisation by regular noise
- Regularization independent of the noise level: an analysis of quasi-optimality
- Enhancing linear regularization to treat large noise
Cites work
- A General Framework for Regularized, Similarity-Based Image Restoration
- A Review of Image Denoising Algorithms, with a New One
- An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse Problems
- BM3D Frames and Variational Image Deblurring
- Boosting of image denoising algorithms
- Convolutional neural networks analyzed via convolutional sparse coding
- Coordinate and subspace optimization methods for linear least squares with non-quadratic regularization
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring Problems
- Fast Image Recovery Using Variable Splitting and Constrained Optimization
- From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images
- Generalizing the Nonlocal-Means to Super-Resolution Reconstruction
- Global Image Denoising
- Higher-Order Feature-Preserving Geometric Regularization
- How to SAIF-ly Boost Denoising Performance
- scientific article; zbMATH DE number 53613 (Why is no real title available?)
- scientific article; zbMATH DE number 1465030 (Why is no real title available?)
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 3239667 (Why is no real title available?)
- scientific article; zbMATH DE number 961607 (Why is no real title available?)
- Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization
- Image restoration via simultaneous sparse coding: where structured sparsity meets Gaussian scale mixture
- Is Denoising Dead?
- Local and nonlocal discrete regularization on weighted graphs for image and mesh processing
- Non-local regularization of inverse problems
- Nonlinear total variation based noise removal algorithms
- Nonlocal discrete p-Laplacian driven image and manifold processing
- Nonlocally Centralized Sparse Representation for Image Restoration
- Patch-Based Near-Optimal Image Denoising
- Perturbation of the eigenvectors of the graph Laplacian: application to image denoising
- Postprocessing of Compressed Images via Sequential Denoising
- Principal Neighborhood Dictionaries for Nonlocal Means Image Denoising
- Progressive Image Denoising
- Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A Unified Framework
- Regularization on graphs with function-adapted diffusion processes
- Secrets of image denoising cuisine
- Solving Inverse Problems With Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity
- Sparse and redundant representations. From theory to applications in signal and image processing.
- Sparse Representation Based Image Interpolation With Nonlocal Autoregressive Modeling
- Symmetric Smoothing Filters From Global Consistency Constraints
- Symmetrizing smoothing filters
- The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
Cited in
(only showing first 100 items - show all)- redR
- Whiteness constraints in a unified variational framework for image restoration
- Blind Poissonian image deblurring regularized by a denoiser constraint and deep image prior
- A support-denoiser-driven framework for single image restoration
- Remove the salt and pepper noise based on the high order total variation and the nuclear norm regularization
- Constrained and unconstrained deep image prior optimization models with automatic regularization
- Plug-and-play gradient-based denoisers applied to CT image enhancement
- Speckle reduction in matrix-log domain for synthetic aperture radar imaging
- Regularization methods in the analysis of a series of scintillation fluorescence microscopy images
- Deep learning for inverse problems. Abstracts from the workshop held March 7--13, 2021 (hybrid meeting)
- Designing rotationally invariant neural networks from PDEs and variational methods
- Multi-frame super resolution via deep plug-and-play CNN regularization
- Convolutional proximal neural networks and plug-and-play algorithms
- Effective new methods for automated parameter selection in regularized inverse problems
- RTR-DPD: reweighted Tikohonov regularization for blind deblurring via dual principles of discriminativeness
- Patch ordering as a regularization for inverse problems in image processing
- Accelerating Proximal Markov Chain Monte Carlo by Using an Explicit Stabilized Method
- Rate-optimal denoising with deep neural networks
- Regularization theory of the analytic deep prior approach
- scientific article; zbMATH DE number 7625169 (Why is no real title available?)
- Patch-based image restoration using expectation propagation
- Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
- Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
- NETT: solving inverse problems with deep neural networks
- Compressive Computed Tomography Reconstruction through Denoising Approximate Message Passing
- Deep synthesis network for regularizing inverse problems
- An image reconstruction model regularized by edge-preserving diffusion and smoothing for limited-angle computed tomography
- Plug-and-Play Unplugged: Optimization-Free Reconstruction Using Consensus Equilibrium
- Denoising AMP for MRI reconstruction: BM3D-AMP-MRI
- Modern regularization methods for inverse problems
- Solving inverse problems using data-driven models
- Rendition: reclaiming what a black box takes away
- Regularization by denoising via fixed-point projection (RED-PRO)
- Joint Gaussian dictionary learning and tomographic reconstruction
- An Unrolled Implicit Regularization Network for Joint Image and Sensitivity Estimation in Parallel MR Imaging with Convergence Guarantee
- An introduction to the mathematics of deep learning
- A literature survey of matrix methods for data science
- Image Denoising: The Deep Learning Revolution and Beyond—A Survey Paper
- Deep-plug-and-play proximal Gauss-Newton method with applications to nonlinear, ill-posed inverse problems
- Joint demosaicking and denoising benefits from a two-stage training strategy
- Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling
- Self-Supervised Deep Learning for Image Reconstruction: A Langevin Monte Carlo Approach
- Regularising inverse problems with generative machine learning models
- On maximum a posteriori estimation with Plug \& Play priors and stochastic gradient descent
- WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution
- Inversion of Band-Limited Discrete Fourier Transforms of Binary Images: Uniqueness and Algorithms
- Explainable bilevel optimization: an application to the Helsinki Deblur Challenge
- Improving image deblurring
- Preconditioned Plug-and-Play ADMM with Locally Adjustable Denoiser for Image Restoration
- PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descent
- Computational Imaging Through Atmospheric Turbulence
- The mathematics of artificial intelligence
- Learning sparsity-promoting regularizers using bilevel optimization
- NF-ULA: normalizing flow-based unadjusted Langevin algorithm for imaging inverse problems
- Convergent data-driven regularizations for CT reconstruction
- Three-operator splitting for learning to predict equilibria in convex games
- Adaptive total variational regularization of Gaussian denoisers for multiplicative noise removal
- Averaged deep denoisers for image regularization
- Modular ADMM-based strategies for optimized compression, restoration, and distributed representations of visual data
- Learned regularizers for inverse problems
- Iterative gradient denoising algorithm for signal recovery using analysis-based implicit prior
- Normalizing flow regularization for photoacoustic tomography
- Review of diffusion models: theory and applications
- Robustness and exploration of variational and machine learning approaches to inverse problems: an overview
- Neural-network-based regularization methods for inverse problems in imaging
- HyDeFuse: provably convergent denoiser-driven hyperspectral fusion
- Analysis and synthesis denoisers for forward-backward plug-and-play algorithms
- Adaptive reference constrained regularization by denoising for image restoration
- Plug and Play splitting techniques for Poisson image restoration
- Practical operator sketching framework for accelerating iterative data-driven solutions in linear inverse problems
- Stochastic primal-dual three operator splitting algorithm with extension to equivariant regularization-by-denoising
- Convergence analysis of a proximal stochastic denoising regularization algorithm
- Equivariant denoisers for image restoration
- Enhanced denoising and convergent regularisation using Tweedie scaling
- A Modular Deep Learning-based Approach for Diffuse Optical Tomography Reconstruction
- \texttt{TAEN}: a model-constrained Tikhonov autoencoder network for forward and inverse problems
- Mathematical imaging and surface processing. Abstracts from the workshop held February 2--7, 2025
- Convergent regularization in inverse problems and linear plug-and-play denoisers
- HPPP: Halpern-type preconditioned proximal point algorithms and applications to image restoration
- Joint structure-texture low-dimensional modeling for image decomposition with a plug-and-play framework
- A guide to stochastic optimisation for large-scale inverse problems
- Efficient model-based deep learning via network pruning and fine-tuning
- Subspace diffusion posterior sampling for travel-time tomography
- Data-driven methods for quantitative imaging
- Wavelet analysis model inspired convolutional neural networks for image denoising
- Advanced reference-constrained image restoration algorithm
- Convergent plug-and-play with proximal denoiser and unconstrained regularization parameter
- Product of Gaussian mixture diffusion models
- Short communication: FISTA iterates converge linearly for denoiser-driven regularization
- Inverse problems in image restoration
- Unrolling deep learning end-to-end method for phase retrieval
- Optimal regularization for a data source
- On the convergence of the iterative regularization method assisted by the graph Laplacian with early stopping
- Connecting image inpainting with denoising in the homogeneous diffusion setting
- Dip-based anisotropic total variation regularization for image denoising
- A Relaxed Gradient Step Denoiser for Splitting Methods in Poisson Inverse Problems
- Deep equilibrium models for Poisson imaging inverse problems via mirror descent
- Incomplete data multisource static computed tomography reconstruction with diffusion priors and implicit neural representation
- Efficient Bayesian computation using plug-and-play priors for Poisson inverse problems
- Inertial proximal difference-of-convex algorithm with convergent Bregman plug-and-play for nonconvex imaging
This page was built for publication: The Little Engine that Could: Regularization by Denoising (RED)
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q148569)
