SHI, Hui; TRAONMILIN, Yann; AUJOL, Jean François

Métadonnées

Afficher la notice complète

Licence d’utilisation du document

SHI, Hui
Institut de Mathématiques de Bordeaux [IMB]

TRAONMILIN, Yann
Institut de Mathématiques de Bordeaux [IMB]

AUJOL, Jean François
Institut de Mathématiques de Bordeaux [IMB]

Langue

Communication dans un congrès

Ce document a été publié dans

International Conference on Scale Space and Variational Methods in Computer Vision (SSVM), 2023-05-21, Cagliari.

Résumé en anglais

Solving ill-posed inverse problems can be done accurately if a regularizer well adapted to the nature of the data is available. Such regularizer can be systematically linked with the distribution of the data itself through the maximum a posteriori Bayesian framework. Recently, regularizers designed with the help of deep neural networks received impressive success. Such regularizers are typically learned from voluminous training data. To reduce the computational burden of this task, we propose to adapt the compressive learning framework to the learning of regularizers parametrized by deep neural networks (DNN). Our work shows the feasibility of batchless learning of regularizers from a compressed dataset. In order to achieve this, we propose an approximation of the compression operator that can be calculated explicitly for the task of learning a regularizer by DNN. We show that the proposed regularizer is capable of modeling complex regularity prior and can be used to solve the denoising inverse problem.< Réduire

URI

https://oskar-bordeaux.fr/handle/20.500.12278/190612

Project ANR

Régularisation performante de problèmes inverses en grande dimension pour le traitement de données - ANR-20-CE40-0001

Origine

Importé de hal

Unités de recherche

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251