Shared Prior Learning of Energy-Based Models for Image Reconstruction
DOI10.1137/20M1380016OpenAlexW3213875378MaRDI QIDQ5860383
Thomas Pinetz, Thomas Pock, Alexander Effland, Erich Kobler
Publication date: 19 November 2021
Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2011.06539
gradient flowWasserstein distanceoptimal transportdeep learningconvolutional neural networkmean-field optimal controlmosco convergenceenergy-based learningshared prior learning
Numerical optimization and variational techniques (65K10) Computing methodologies for image processing (68U10) Numerical solutions to stochastic differential and integral equations (65C30) Numerical solution of inverse problems involving ordinary differential equations (65L09)
Related Items (1)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Computational Optimal Transport: With Applications to Data Science
- Nonlinear total variation based noise removal algorithms
- Filtering, segmentation and depth
- Fields of experts
- An introduction to \(\Gamma\)-convergence
- Image recovery via total variation minimization and related problems
- The nonlinear statistics of high-contrast patches in natural images
- Variational networks: an optimal control approach to early stopping variational methods for image restoration
- Mathematical image processing. Translated from the German
- Directional total generalized variation regularization
- A mean-field optimal control formulation of deep learning
- Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
- A proposal on machine learning via dynamical systems
- Total roto-translational variation
- Convergence of convex sets and of solutions of variational inequalities
- Model distortions in Bayesian MAP reconstruction
- On Bayesian estimation and proximity operators
- Augmented Lagrangian Method, Dual Methods, and Split Bregman Iteration for ROF, Vectorial TV, and High Order Models
- Stochastic models for generic images
- High-Order Total Variation-Based Image Restoration
- Joint Demosaicing and Denoising via Learned Nonparametric Random Fields
- Class-Aware Fully Convolutional Gaussian and Poisson Denoising
- DeepISP: Toward Learning an End-to-End Image Processing Pipeline
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Wasserstein Dictionary Learning: Optimal Transport-Based Unsupervised Nonlinear Dictionary Learning
- The quadratic Wasserstein metric for inverse data matching
- Semi-Supervised Image Dehazing
- Deep Graph-Convolutional Image Denoising
- Higher-Order Total Directional Variation: Analysis
- NETT: solving inverse problems with deep neural networks
- Structure Tensor Total Variation
- Iterative Bregman Projections for Regularized Transportation Problems
- A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
- First Order Algorithms in Variational Image Processing
- An introduction to continuous optimization for imaging
- Total Generalized Variation
- Optimal Transport
- Direct methods in the calculus of variations
This page was built for publication: Shared Prior Learning of Energy-Based Models for Image Reconstruction
