Semi-Discrete Optimal Transport in Patch Space for Enriching Gaussian Textures

Abstract : A bilevel texture model is proposed, based on a local transform of a Gaussian random field. The core of this method relies on the optimal transport of a continuous Gaussian distribution towards the discrete exemplar patch distribution. The synthesis then simply consists in a fast post-processing of a Gaussian texture sample, boiling down to an improved nearest-neighbor patch matching, while offering theoretical guarantees on statistical compliancy.
Type de document :
Communication dans un congrès
Geometric Science of Information, Nov 2017, Paris, France. Lecture Notes in Computer Science, Geometric Science of Information, 10589, 2017, Lecture Notes in Computer Science. 〈https://link.springer.com/book/10.1007/978-3-319-68445-1〉. 〈10.1007/978-3-319-68445-1_12〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01560785
Contributeur : Bruno Galerne <>
Soumis le : mardi 11 juillet 2017 - 23:36:25
Dernière modification le : mardi 5 juin 2018 - 10:14:42
Document(s) archivé(s) le : mercredi 24 janvier 2018 - 22:18:07

Fichier

GLR_semi_discrete_OT_in_patch_...
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Bruno Galerne, Arthur Leclaire, Julien Rabin. Semi-Discrete Optimal Transport in Patch Space for Enriching Gaussian Textures. Geometric Science of Information, Nov 2017, Paris, France. Lecture Notes in Computer Science, Geometric Science of Information, 10589, 2017, Lecture Notes in Computer Science. 〈https://link.springer.com/book/10.1007/978-3-319-68445-1〉. 〈10.1007/978-3-319-68445-1_12〉. 〈hal-01560785〉

Partager

Métriques

Consultations de la notice

341

Téléchargements de fichiers

213