Inverse problem regularization with hierarchical variational autoencoders
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | PROST, Jean | |
| hal.structure.identifier | Ubisoft | |
| dc.contributor.author | HOUDARD, Antoine | |
| hal.structure.identifier | Mathématiques Appliquées Paris 5 [MAP5 - UMR 8145] | |
| dc.contributor.author | ALMANSA, Andres | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| hal.structure.identifier | Modélisation Mathématique pour l'Oncologie [MONC] | |
| dc.contributor.author | PAPADAKIS, Nicolas | |
| dc.date.accessioned | 2024-04-04T02:34:52Z | |
| dc.date.available | 2024-04-04T02:34:52Z | |
| dc.date.issued | 2023-03-20 | |
| dc.date.conference | 2023-10-02 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/190583 | |
| dc.description.abstractEn | 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. | |
| dc.description.sponsorship | Repenser la post-production d'archives avec des méthodes à patch, variationnelles et par apprentissage - ANR-19-CE23-0027 | |
| dc.language.iso | en | |
| dc.title.en | Inverse problem regularization with hierarchical variational autoencoders | |
| dc.type | Communication dans un congrès | |
| dc.subject.hal | Informatique [cs] | |
| dc.identifier.arxiv | 2303.11217 | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.conference.title | IEEE International Conference on Computer Vision (ICCV'23) | |
| bordeaux.country | FR | |
| bordeaux.conference.city | Paris | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-04038644 | |
| hal.version | 1 | |
| hal.invited | non | |
| hal.proceedings | oui | |
| hal.conference.end | 2023-10-06 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-04038644v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2023-03-20&rft.au=PROST,%20Jean&HOUDARD,%20Antoine&ALMANSA,%20Andres&PAPADAKIS,%20Nicolas&rft.genre=unknown |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||