Optimal transport between GMM for multiscale texture synthesis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Optimal transport between GMM for multiscale texture synthesis

Résumé

Using optimal transport in image processing tasks has become very popular. However, it still faces difficult computational issues when dealing with high-dimensional distributions. We propose here to use the recently introduced GMM-OT formulation, which consists in restricting the optimal transport problem to the set of Gaussian mixture models. As a proof of concept, we use it to improve the texture model Texto based on optimal transport between distributions of image patches. Using GMM-OT in this texture model allows to deal with larger patches, hence providing results with better geometric details. This new model allows for synthesis, mixing, and style transfer.
Fichier principal
Vignette du fichier
main_SSVM_hal.pdf (41.53 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03613622 , version 1 (18-03-2022)
hal-03613622 , version 2 (01-06-2023)

Identifiants

Citer

Julie Delon, Agnès Desolneux, Laurent Facq, Arthur Leclaire. Optimal transport between GMM for multiscale texture synthesis. International Conference on Scale Space and Variational Methods in Computer Vision (SSVM), Luca Calatroni; Marco Donatelli; Serena Morigi; Marco Prato; Giuseppe Rodriguez; Matteo Santacesaria, May 2023, Cagliari, Italy. ⟨10.1007/978-3-031-31975-4_48⟩. ⟨hal-03613622v2⟩
211 Consultations
25 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More