|
Title:
|
Wasserstein Barycenter and its Application to Texture Mixing |
|
Author:
|
Bernot, Marc; Rabin, Julien; Peyré, Gabriel; Delon, Julie |
|
Type:
|
Communication / Conférence
|
|
Date de création:
|
2012 |
|
Pages:
|
435-446 |
|
Résumé en anglais:
|
This paper proposes a new definition of the averaging of discrete probability distributions as a barycenter over the Wasserstein space. Replacing the Wasserstein original metric by a sliced approximation over 1D distributions allows us to use a fast stochastic gradient descent algorithm. This new notion of barycenter of probabilities is likely to find applications in computer vision where one wants to average features defined as distributions. We show an application to texture synthesis and mixing, where a texture is characterized by the distribution of the response to a multiscale oriented filter bank. This leads to a simple way to navigate over a convex domain of color textures. |
|
Description
:
|
LNCS n°6667, http://dx.doi.org/10.1007/978-3-642-24785-9_37 |
|
Lien vers un document non conservé dans cette base:
|
http://hal.archives-ouvertes.fr/hal-00476064/fr/
|
|
Indexation documentaire:
|
Traitement du signal |
|
Sujet(s):
|
image processing; stochastic gradient; Wasserstein barycenter; optimal transport; texture synthesis; texture mixing |
|
URL de la notice:
|
http://basepub.dauphine.fr/xmlui/handle/123456789/4053 |
|
Titre du colloque:
|
Third International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2011) |
|
Date du colloque:
|
05-2011 |
|
Ville du colloque:
|
Ein-Gedi |
|
Pays du colloque:
|
Israël |
|
PUBLIE DANS
|
|
Titre de l'ouvrage:
|
Scale Space and Variational Methods in Computer Vision
Third International Conference, SSVM 2011, Ein-Gedi, Israel, May 29 – June 2, 2011, Revised Selected Papers |
|
Author:
|
Bruckstein, Alfred M.; Ter Haar Romeny, Bart M.; Bronstein, Alexander M.; Bronstein, Michael M. |
|
Editeur:
|
Springer |
|
Ville d'édition:
|
Berlin |
|
Parution:
|
2012 |
|
Nombre de pages:
|
798 |
|
ISBN:
|
978-3-642-24784-2 |
|
URL de l'ouvrage:
|
http://dx.doi.org/10.1007/978-3-642-24785-9
|