Learning local regularization for variational image restoration - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Learning local regularization for variational image restoration

Jean Prost
  • Function : Author
  • PersonId : 1084606
Antoine Houdard
Andrés Almansa

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.
Fichier principal
Vignette du fichier
learning_local_regularization.pdf (2.97 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03139784 , version 1 (12-02-2021)

Identifiers

Cite

Jean Prost, Antoine Houdard, Andrés Almansa, Nicolas Papadakis. Learning local regularization for variational image restoration. International Conference on Scale Space and Variational Methods in Computer Vision (SSVM'21), May 2021, Cabourg, France. pp.358-370, ⟨10.1007/978-3-030-75549-2_29⟩. ⟨hal-03139784⟩
149 View
93 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More