A Texton for Fast and Flexible Gaussian Texture Synthesis

Abstract : Gaussian textures can be easily simulated by convolving an initial image sample with a conveniently normalized white noise. However, this procedure is not very flexible (it does not allow for non-uniform grids in particular), and can become computationally heavy for large domains. We here propose an algorithm that summarizes a texture sample into a synthesis-oriented texton, that is, a small image for which the discrete spot noise simulation (summed and normalized randomly-shifted copies of the texton) is more efficient than the classical convolution algorithm. Using this synthesis-oriented texture summary, Gaussian textures can be generated in a faster, simpler, and more flexible way.
Type de document :
Communication dans un congrès
European Signal Processing Conference, Sep 2014, Lisbon, Portugal. Proceedings of the 22nd European Signal Processing Conference (EUSIPCO), pp. 1686-1690
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-00957746
Contributeur : Lionel Moisan <>
Soumis le : mardi 11 mars 2014 - 00:29:02
Dernière modification le : lundi 24 octobre 2016 - 15:25:49
Document(s) archivé(s) le : mercredi 11 juin 2014 - 10:50:45

Fichier

2014-08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00957746, version 1

Collections

Citation

Bruno Galerne, Arthur Leclaire, Lionel Moisan. A Texton for Fast and Flexible Gaussian Texture Synthesis. European Signal Processing Conference, Sep 2014, Lisbon, Portugal. Proceedings of the 22nd European Signal Processing Conference (EUSIPCO), pp. 1686-1690. <hal-00957746>

Partager

Métriques

Consultations de
la notice

281

Téléchargements du document

188