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

Abstract

Exploiting image patches instead of whole images have proved to be a powerful approach to tackle various problems in image processing. Recently, Wasserstein patch priors (WPP), which are based on the comparison of the patch distributions of the unknown image and a reference image, were successfully used as data-driven regularizers in the variational formulation of superresolution. However, for each input image, this approach requires the solution of a non-convex minimization problem which is computationally costly. In this paper, we propose to learn two kind of neural networks in an unsupervised way based on WPP loss functions. First, we show how convolutional neural networks (CNNs) can be incorporated. Once the network, called WPPNet, is learned, it can be very efficiently applied to any input image. Second, we incorporate conditional normalizing flows to provide a tool for uncertainty quantification. Numerical examples demonstrate the very good performance of WPPNets for superresolution in various image classes even if the forward operator is known only approximately.

References in corpus (8)

• General state space Markov chains and MCMC algorithms
• CNN-Based Projected Gradient Descent for Consistent Image Reconstruction
• Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods
• Convolutional Proximal Neural Networks and Plug-and-Play Algorithms
• Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpoint
• Wasserstein Patch Prior for Image Superresolution
• A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions
• The basins of attraction of the global minimizers of non-convex inverse problems with low-dimensional models in infinite dimension

Cited by in corpus (5)

• PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
• Generalized Normalizing Flows via Markov Chains
• Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problems
• Proximal Residual Flows for Bayesian Inverse Problems
• Mixed Noise and Posterior Estimation with Conditional DeepGEM