Self-Supervised Deep Learning for Image Reconstruction: A Langevin Monte Carlo Approach

Artificial neural networks and deep learning (68T07) Monte Carlo methods (65C05) Computing methodologies for image processing (68U10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Stochastic methods (Fokker-Planck, Langevin, etc.) applied to problems in time-dependent statistical mechanics (82C31)

Cites Work

Unnamed Item
Unnamed Item
Nonlinear total variation based noise removal algorithms
The Little Engine that Could: Regularization by Denoising (RED)
Wavelet frame based blind image inpainting
Exponential convergence of Langevin distributions and their discrete approximations
Langevin diffusions and Metropolis-Hastings algorithms
Some qualitative properties for the total variation flow
A geometric analysis of phase retrieval
Convolutional proximal neural networks and plug-and-play algorithms
Data-driven tight frame construction and image denoising
Universality of deep convolutional neural networks
High-dimensional Bayesian inference via the unadjusted Langevin algorithm
The Mathematics of Computerized Tomography
Phase Retrieval via Wirtinger Flow: Theory and Algorithms
Stochastic gradient Langevin dynamics with adaptive drifts
Should Penalized Least Squares Regression be Interpreted as Maximum A Posteriori Estimation?
$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo: When Langevin Meets Moreau
Stochastic Normalizing Flows for Inverse Problems: A Markov Chains Viewpoint
Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
Image restoration: Total variation, wavelet frames, and beyond
Breaking the Curse of Dimensionality with Convex Neural Networks
Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring Problems
Compressed sensing
Handbook of stochastic methods for physics, chemistry and the natural sciences.