Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
From MaRDI portal
Publication:5094622
DOI10.1137/21M1406313MaRDI QIDQ5094622FDOQ5094622
Authors:
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/2103.10182
Recommendations
- Bayesian MLP neural networks for image analysis
- Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
- Bayesian neural network priors for edge-preserving inversion
- Hypermodels in the Bayesian imaging framework
- A Bayesian approach to synthetic magnetic resonance imaging
- Bayesian image analysis
- Bilevel approaches for learning of variational imaging models
Bayesian inferencemachine learningMarkov chain Monte Carlo methodsinverse problemsmathematical imaging
Bayesian inference (62F15) Computing methodologies for image processing (68U10) Numerical solution to inverse problems in abstract spaces (65J22)
Cites Work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- Benchmark problems for phase retrieval
- The Bayesian Choice
- Weak convergence and optimal scaling of random walk Metropolis algorithms
- Statistical and computational inverse problems.
- A Stochastic Approximation Method
- Towards optimal scaling of Metropolis-coupled Markov chain Monte Carlo
- The Little Engine that Could: Regularization by Denoising (RED)
- Fast Image Recovery Using Variable Splitting and Constrained Optimization
- Regularization by denoising via fixed-point projection (RED-PRO)
- Marginal Likelihood Estimation via Power Posteriors
- Perturbation theory for Markov chains via Wasserstein distance
- Invariant HPD credible sets and MAP estimators
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- MCMC methods for functions: modifying old algorithms to make them faster
- Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion
- An introduction to continuous optimization for imaging
- On the well-posedness of Bayesian inverse problems
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- NETT: solving inverse problems with deep neural networks
- Solving inverse problems using data-driven models
- High-dimensional mixture models for unsupervised image denoising (HDMI)
- Model distortions in Bayesian MAP reconstruction
- Posterior expectation of the total variation model: properties and experiments
- BigGAN
- Testing the manifold hypothesis
- From Denoising to Compressed Sensing
- Accelerating Proximal Markov Chain Monte Carlo by Using an Explicit Stabilized Method
- Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau
- Vector Approximate Message Passing
- Enhancing compressed sensing 4D photoacoustic tomography by simultaneous motion estimation
- Plug in estimation in high dimensional linear inverse problems a rigorous analysis
Cited In (10)
- NF-ULA: normalizing flow-based unadjusted Langevin algorithm for imaging inverse problems
- Efficient Bayesian Computation for Low-Photon Imaging Problems
- Generative models and Bayesian inversion using Laplace approximation
- Bayesian imaging inverse problem with SA-roundtrip prior via HMC-pCN sampler
- Uncertainty quantification using Bayesian neural networks in classification: application to biomedical image segmentation
- Enhancing electrical impedance tomography reconstruction using learned half-quadratic splitting networks with Anderson acceleration
- Bayesian Inverse Problems Are Usually Well-Posed
- Solving Bayesian inverse problems using neural networks
- Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
- Neural-network-based regularization methods for inverse problems in imaging
Uses Software
This page was built for publication: Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5094622)
