Mostrar el registro sencillo del ítem
Efficient Posterior Sampling For Diverse Super-Resolution with Hierarchical VAE Prior
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, Andrés | |
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 | 2024-04-04T02:30:47Z | |
dc.date.available | 2024-04-04T02:30:47Z | |
dc.date.conference | 2024-02-27 | |
dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/190266 | |
dc.description.abstractEn | We investigate the problem of producing diverse solutions to an image super-resolution problem.From a probabilistic perspective, this can be done by sampling from the posterior distribution of an inverse problem, which requires the definition of a prior distribution on the high-resolution images. In this work, we propose to use a pretrained hierarchical variational autoencoder (HVAE) as a prior. We train a lightweight stochastic encoder to encode low-resolution images in the latent space of a pretrained HVAE. At inference, we combine the low-resolution encoder and the pretrained generative model to super-resolve an image. We demonstrate on the task of face super-resolution that our method provides an advantageous trade-off between the computational efficiency of conditional normalizing flows techniques and the sample quality of diffusion based methods. | |
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 | Efficient Posterior Sampling For Diverse Super-Resolution with Hierarchical VAE Prior | |
dc.type | Communication dans un congrès | |
dc.identifier.doi | 10.5220/0012352800003660 | |
dc.subject.hal | Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV] | |
dc.identifier.arxiv | 2205.10347v4 | |
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 | VISAPP 2024 - 19th International Conference on Computer Vision Theory and Applications | |
bordeaux.country | IT | |
bordeaux.conference.city | Rome | |
bordeaux.peerReviewed | oui | |
hal.identifier | hal-03675314 | |
hal.version | 1 | |
hal.invited | non | |
hal.proceedings | oui | |
hal.conference.end | 2024-02-29 | |
hal.popular | non | |
hal.audience | Internationale | |
hal.origin.link | https://hal.archives-ouvertes.fr//hal-03675314v1 | |
bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=PROST,%20Jean&HOUDARD,%20Antoine&ALMANSA,%20Andr%C3%A9s&PAPADAKIS,%20Nicolas&rft.genre=unknown |
Archivos en el ítem
Archivos | Tamaño | Formato | Ver |
---|---|---|---|
No hay archivos asociados a este ítem. |