WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution

DOI10.1137/22m1496542zbMath1517.94016arXiv2201.08157OpenAlexW4384036044MaRDI QIDQ6168325

Unnamed Author, Johannes Hertrich

Publication date: 8 August 2023

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

Full work available at URL: https://arxiv.org/abs/2201.08157

zbMATH Keywords

superresolutionnormalizing flowsunsupervised neural network trainingWasserstein patch prior

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Bayesian inference (62F15) Bayesian problems; characterization of Bayes procedures (62C10) Computing methodologies for image processing (68U10) Reasoning under uncertainty in the context of artificial intelligence (68T37) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Optimal transportation (49Q22)

Related Items (1)

Image super-resolution with PCA reduced generalized Gaussian mixture models in materials science

Cites Work

• The Little Engine that Could: Regularization by Denoising (RED)
• Wasserstein generative models for patch-based texture synthesis
• Invertible neural networks versus MCMC for posterior reconstruction in grazing incidence X-ray fluorescence
• General state space Markov chains and MCMC algorithms
• On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
• Variational networks: an optimal control approach to early stopping variational methods for image restoration
• PCA reduced Gaussian mixture models with applications in superresolution
• Convolutional proximal neural networks and plug-and-play algorithms
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• A Nonlocal Bayesian Image Denoising Algorithm
• Cubic convolution interpolation for digital image processing
• Single Image Super Resolution using a Joint GMM Method
• Accelerating GMM-Based Patch Priors for Image Restoration: Three Ingredients for a <inline-formula> <tex-math notation="LaTeX">$100{\times}$ </tex-math> </inline-formula> Speed-Up
• Compressive Learning for Patch-Based Image Denoising
• Stochastic Normalizing Flows for Inverse Problems: A Markov Chains Viewpoint
• Generalized Normalizing Flows via Markov Chains
• Computed tomography reconstruction using deep image prior and learned reconstruction methods
• High-Dimensional Mixture Models for Unsupervised Image Denoising (HDMI)
• FSIM: A Feature Similarity Index for Image Quality Assessment
• Signal Recovery by Proximal Forward-Backward Splitting
• A Review of Image Denoising Algorithms, with a New One
• Shared Prior Learning of Energy-Based Models for Image Reconstruction
• Proximal Splitting Algorithms for Convex Optimization: A Tour of Recent Advances, with New Twists
• A generative model for texture synthesis based on optimal transport between feature distributions

This page was built for publication: WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution