Self-Supervised Deep Learning for Image Reconstruction: A Langevin Monte Carlo Approach
From MaRDI portal
Publication:6144068
Monte Carlo methods (65C05) Artificial neural networks and deep learning (68T07) Computing methodologies for image processing (68U10) Stochastic methods (Fokker-Planck, Langevin, etc.) applied to problems in time-dependent statistical mechanics (82C31) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Recommendations
- Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling
- Un-supervised learning for blind image deconvolution via Monte-Carlo sampling
- Unsupervised knowledge-transfer for learned image reconstruction
- Reversible Autoencoder: A CNN-Based Nonlinear Lifting Scheme for Image Reconstruction
- Adversarially learned iterative reconstruction for imaging inverse problems
- Deep Generative Models and Inverse Problems
- Digital core image reconstruction based on residual self-attention generative adversarial networks
- Generative model of autoencoders self-learning on images represented by count samples
Cites work
- rm K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
- A geometric analysis of phase retrieval
- An introduction to total variation for image analysis
- Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
- Breaking the curse of dimensionality with convex neural networks
- Compressed sensing
- Convolutional proximal neural networks and plug-and-play algorithms
- Data-driven tight frame construction and image denoising
- Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau
- Exponential convergence of Langevin distributions and their discrete approximations
- Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring Problems
- Handbook of stochastic methods for physics, chemistry and the natural sciences.
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- Image restoration: total variation, wavelet frames, and beyond
- Langevin diffusions and Metropolis-Hastings algorithms
- Nonlinear total variation based noise removal algorithms
- Phase retrieval via Wirtinger flow: theory and algorithms
- Should Penalized Least Squares Regression be Interpreted as Maximum A Posteriori Estimation?
- Some qualitative properties for the total variation flow
- Stochastic gradient Langevin dynamics with adaptive drifts
- Stochastic normalizing flows for inverse problems: a Markov chains viewpoint
- The Little Engine that Could: Regularization by Denoising (RED)
- The mathematics of computerized tomography
- Universality of deep convolutional neural networks
- Wavelet frame based blind image inpainting
- What regularized auto-encoders learn from the data-generating distribution
Cited in
(14)- Generative model of autoencoders self-learning on images represented by count samples
- Un-supervised learning for blind image deconvolution via Monte-Carlo sampling
- Reversible Autoencoder: A CNN-Based Nonlinear Lifting Scheme for Image Reconstruction
- Shared Prior Learning of Energy-Based Models for Image Reconstruction
- A dataset-free deep learning method for low-dose CT image reconstruction
- Bayesian imaging inverse problem with SA-roundtrip prior via HMC-pCN sampler
- PhaseNet: a deep learning based phase reconstruction method for ground-based astronomy
- Efficient Bayesian deep inversion
- Diffusion posterior sampling for magnetic resonance imaging
- PALADIN: a novel plug-and-play 3D CS-MRI reconstruction method
- Efficient image restoration via non-convex total variation regularization and ADMM optimization
- Efficient image restoration using generalized non-convex total variation regularization and Chebyshev-accelerated ADMM
- Efficient Chebyshev-optimized ADMM algorithm for image restoration using Nesterov acceleration
- Poisson noise removal via a non-convex log total variation regularization
This page was built for publication: Self-Supervised Deep Learning for Image Reconstruction: A Langevin Monte Carlo Approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6144068)
