mlsanityData to 7 Oct 2026

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

arXiv 2201.08157 ↗First posted 20 Jan 2022cs.CV cs.LG eess.IVcited by 10

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 43 of its 75 references that are in the map. First posted on arXiv 20 Jan 2022.

Builds on

43 of 75 references.

References · 43

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2015Variational Inference with Normalizing Flowscited by 2,161
  4. 2016Density estimation using Real NVPcited by 2,029
  5. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  6. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  8. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  9. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  10. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  11. 2017Deep Image Priorcited by 1,097
  12. 2018Residual Dense Network for Image Super-Resolutioncited by 796
31 more
  1. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  2. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  3. 2019Deep Learning for Image Super-resolution: A Surveycited by 368
  4. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
  5. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  6. 2019Residual Flows for Invertible Generative Modelingcited by 256
  7. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 244
  8. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  9. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  10. 2017Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problemscited by 107
  11. 2017CNN-Based Projected Gradient Descent for Consistent Image Reconstructioncited by 75
  12. 2020Deep Probabilistic Imaging: Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imagingcited by 57
  13. 2020Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methodscited by 56
  14. 2020Total Deep Variation for Linear Inverse Problemscited by 53
  15. 2020Convolutional Proximal Neural Networks and Plug-and-Play Algorithmscited by 36
  16. 2021Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpointcited by 32
  17. 2019HINT: Hierarchical Invertible Neural Transport for Density Estimation and Bayesian Inferencecited by 31
  18. 2016RAISR: Rapid and Accurate Image Super Resolutioncited by 27
  19. 2021Conditional Invertible Neural Networks for Diverse Image-to-Image Translationcited by 24
  20. 2021Generalized Normalizing Flows via Markov Chainscited by 23
  21. 2021Conditional Invertible Neural Networks for Medical Imagingcited by 19
  22. 2021Asymmetric CNN for image super-resolutioncited by 14
  23. 2021Wasserstein Patch Prior for Image Superresolutioncited by 13
  24. 2020PCA Reduced Gaussian Mixture Models with Applications in Superresolutioncited by 12
  25. 2021Invertible Neural Networks versus MCMC for Posterior Reconstruction in Grazing Incidence X-Ray Fluorescencecited by 12
  26. 2020A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributionscited by 11
  27. 2021Understanding approximate and unrolled dictionary learning for pattern recoverycited by 11
  28. 2020A deep primal-dual proximal network for image restorationcited by 9
  29. 2017Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100× speed-upcited by 5
  30. 2020Shared Prior Learning of Energy-Based Models for Image Reconstructioncited by 5
  31. 2021Posterior Sampling for Image Restoration using Explicit Patch Priorscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 4; 2025: 0; 2026: 1.

10 papers.

  1. 2023Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernelcited by 25
  2. 2022PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularizationcited by 22
  3. 2023Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problemscited by 17
  4. 2023Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problemscited by 12
  5. 2023Learning from small data sets: Patch-based regularizers in inverse problems for image reconstructioncited by 9
  6. 2024Importance Corrected Neural JKO Samplingcited by 7
  7. 2024T-FAKE: Synthesizing Thermal Images for Facial Landmarkingcited by 7
  8. 2024Mixed Noise and Posterior Estimation with Conditional DeepGEMcited by 1
  9. 2024Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overviewcited by 1
  10. 2026Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Imagescited by 0