PROST, Jean; HOUDARD, Antoine; ALMANSA, Andres; PAPADAKIS, Nicolas

Métadonnées

Afficher la notice complète

Licence d’utilisation du document

PROST, Jean
Institut de Mathématiques de Bordeaux [IMB]

HOUDARD, Antoine
Ubisoft

ALMANSA, Andres
Mathématiques Appliquées Paris 5 [MAP5 - UMR 8145]

Langue

Communication dans un congrès

Ce document a été publié dans

IEEE International Conference on Computer Vision (ICCV'23), 2023-10-02, Paris. 2023-03-20

Résumé en anglais

In this paper, we propose to regularize ill-posed inverse problems using a deep hierarchical variational autoencoder (HVAE) as an image prior. The proposed method synthesizes the advantages of i) denoiser-based Plug \& Play approaches and ii) generative model based approaches to inverse problems. First, we exploit VAE properties to design an efficient algorithm that benefits from convergence guarantees of Plug-and-Play (PnP) methods. Second, our approach is not restricted to specialized datasets and the proposed PnP-HVAE model is able to solve image restoration problems on natural images of any size. Our experiments show that the proposed PnP-HVAE method is competitive with both SOTA denoiser-based PnP approaches, and other SOTA restoration methods based on generative models.< Réduire

URI

https://oskar-bordeaux.fr/handle/20.500.12278/190583

Project ANR

Repenser la post-production d'archives avec des méthodes à patch, variationnelles et par apprentissage - ANR-19-CE23-0027

Origine

Importé de hal

Unités de recherche

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251