Plug-and-Play Unplugged: Optimization-Free Reconstruction Using Consensus Equilibrium
From MaRDI portal
Abstract: Regularized inversion methods for image reconstruction are used widely due to their tractability and ability to combine complex physical sensor models with useful regularity criteria. Such methods motivated the recently developed Plug-and-Play prior method, which provides a framework to use advanced denoising algorithms as regularizers in inversion. However, the need to formulate regularized inversion as the solution to an optimization problem limits the possible regularity conditions and physical sensor models. In this paper, we introduce Consensus Equilibrium (CE), which generalizes regularized inversion to include a much wider variety of both forward components and prior components without the need for either to be expressed with a cost function. CE is based on the solution of a set of equilibrium equations that balance data fit and regularity. In this framework, the problem of MAP estimation in regularized inversion is replaced by the problem of solving these equilibrium equations, which can be approached in multiple ways. The key contribution of CE is to provide a novel framework for fusing multiple heterogeneous models of physical sensors or models learned from data. We describe the derivation of the CE equations and prove that the solution of the CE equations generalizes the standard MAP estimate under appropriate circumstances. We also discuss algorithms for solving the CE equations, including ADMM with a novel form of preconditioning and Newton's method. We give examples to illustrate consensus equilibrium and the convergence properties of these algorithms and demonstrate this method on some toy problems and on a denoising example in which we use an array of convolutional neural network denoisers, none of which is tuned to match the noise level in a noisy image but which in consensus can achieve a better result than any of them individually.
Recommendations
- Distributed and consensus optimization for non-smooth image reconstruction
- scientific article; zbMATH DE number 2131802
- Distributed reconstruction via alternating direction method
- Stable optimizationless recovery from phaseless linear measurements
- scientific article; zbMATH DE number 614399
- Efficient Reconstruction of Piecewise Constant Images Using Nonsmooth Nonconvex Minimization
- Reconstruction with Noisy Data: An Approach via Eigenvalue Optimization
- On the problem of optimal reconstruction
- Sparse approximate reconstruction decomposed by two optimization problems
Cites work
- A Model Based Iterative Reconstruction Algorithm For High Angle Annular Dark Field-Scanning Transmission Electron Microscope (HAADF-STEM) Tomography
- A primer on monotone operator methods
- A Review of Image Denoising Algorithms, with a New One
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Convex Analysis
- Convex analysis and monotone operator theory in Hilbert spaces
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Iterative solution of large sparse systems of equations. Transl. from the German
- Jacobian-free Newton-Krylov methods: a survey of approaches and applications.
- Metric selection in fast dual forward-backward splitting
- On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
- Optimal Combination of Image Denoisers
- Proximal splitting methods in signal processing
- Splitting Algorithms for the Sum of Two Nonlinear Operators
- The Little Engine that Could: Regularization by Denoising (RED)
- Tight global linear convergence rate bounds for Douglas-Rachford splitting
Cited in
(21)- A support-denoiser-driven framework for single image restoration
- scientific article; zbMATH DE number 7625169 (Why is no real title available?)
- Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
- Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
- Compressive Computed Tomography Reconstruction through Denoising Approximate Message Passing
- Regularization by denoising via fixed-point projection (RED-PRO)
- 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
- On maximum a posteriori estimation with Plug \& Play priors and stochastic gradient descent
- Convergence Results for Primal-Dual Algorithms in the Presence of Adjoint Mismatch
- PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descent
- Plug-and-play algorithms for convex non-convex regularization: convergence analysis and applications
- Learning sparsity-promoting regularizers using bilevel optimization
- Extrapolated plug-and-play three-operator splitting methods for nonconvex optimization with applications to image restoration
- Modular ADMM-based strategies for optimized compression, restoration, and distributed representations of visual data
- Deep block proximal linearized minimization algorithm for nonconvex inverse problems
- HPPP: Halpern-type preconditioned proximal point algorithms and applications to image restoration
- Advanced reference-constrained image restoration algorithm
- Learning-to-optimize with PAC-Bayesian guarantees: theoretical considerations and practical implementation
- Inertial proximal difference-of-convex algorithm with convergent Bregman plug-and-play for nonconvex imaging
- Sam-DNN: bilevel convergent sequential averaging methods with denoising neural network
This page was built for publication: Plug-and-Play Unplugged: Optimization-Free Reconstruction Using Consensus Equilibrium
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5230401)
