English

Learning local regularization for variational image restoration

Image and Video Processing 2021-02-12 v1 Machine Learning

Abstract

In this work, we propose a framework to learn a local regularization model for solving general image restoration problems. This regularizer is defined with a fully convolutional neural network that sees the image through a receptive field corresponding to small image patches. The regularizer is then learned as a critic between unpaired distributions of clean and degraded patches using a Wasserstein generative adversarial networks based energy. This yields a regularization function that can be incorporated in any image restoration problem. The efficiency of the framework is finally shown on denoising and deblurring applications.

Keywords

Cite

@article{arxiv.2102.06155,
  title  = {Learning local regularization for variational image restoration},
  author = {Jean Prost and Antoine Houdard and Andrés Almansa and Nicolas Papadakis},
  journal= {arXiv preprint arXiv:2102.06155},
  year   = {2021}
}

Comments

12 pages, 5 figures

R2 v1 2026-06-23T23:04:43.937Z