Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior

DOI10.1137/21M140225XOpenAlexW3134296671MaRDI QIDQ5094620

No author found.

Publication date: 4 August 2022

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2103.01648

zbMATH Keywords

inverse problemsBayesian statisticsimage restorationgenerative modelsbiconvex optimizationvariational autoencoders

Mathematics Subject Classification ID

Convex programming (90C25) Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30) Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies for image processing (68U10) Numerical aspects of computer graphics, image analysis, and computational geometry (65D18)

Related Items

Estimating a Potential Without the Agony of the Partition Function ⋮ Regularising inverse problems with generative machine learning models

Uses Software

• PyTorch
• ImageNet
• GitHub
• AlexNet
• DnCNN
• FFDNet
• PULSE
• NVAE

Cites Work

• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• The Little Engine that Could: Regularization by Denoising (RED)
• On the convergence of the exponential multiplier method for convex programming
• An introduction to \(\Gamma\)-convergence
• An algorithm for total variation minimization and applications
• Biconvex sets and optimization with biconvex functions: a survey and extensions
• Proximal Markov chain Monte Carlo algorithms
• A provably convergent scheme for compressive sensing under random generative priors
• Posterior Expectation of the Total Variation Model: Properties and Experiments
• Nonlocal Operators with Applications to Image Processing
• Sparse and Redundant Representations
• DeepISP: Toward Learning an End-to-End Image Processing Pipeline
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• De-noising by soft-thresholding
• A primal–dual hybrid gradient method for nonlinear operators with applications to MRI
• Global Guarantees for Enforcing Deep Generative Priors by Empirical Risk
• An Introduction to Variational Autoencoders
• Plug-and-Play Unplugged: Optimization-Free Reconstruction Using Consensus Equilibrium
• Solving Inverse Problems With Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity
• Total Generalized Variation
• Learning Maximally Monotone Operators for Image Recovery
• Regularization by Denoising via Fixed-Point Projection (RED-PRO)