Learning local regularization for variational image restoration
Langue
en
Communication dans un congrès
Ce document a été publié dans
International Conference on Scale Space and Variational Methods in Computer Vision (SSVM'21), 2021-05-17, Cabourg. 2021-04-30, vol. LNCS 12679, p. 358-370
Springer
Résumé en anglais
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 ...Lire la suite >
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.< Réduire
Mots clés en anglais
image inverse problem
denoising
deblurring
Project ANR
Repenser la post-production d'archives avec des méthodes à patch, variationnelles et par apprentissage - ANR-19-CE23-0027
Origine
Importé de halUnités de recherche