Macrocanonical Models for Texture Synthesis
| hal.structure.identifier | Centre de Mathématiques et de Leurs Applications [CMLA] | |
| dc.contributor.author | DE BORTOLI, Valentin | |
| hal.structure.identifier | Centre de Mathématiques et de Leurs Applications [CMLA] | |
| dc.contributor.author | DESOLNEUX, Agnès | |
| hal.structure.identifier | Institut Denis Poisson [IDP] | |
| dc.contributor.author | GALERNE, Bruno | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | LECLAIRE, Arthur | |
| dc.date.accessioned | 2024-04-04T03:01:28Z | |
| dc.date.available | 2024-04-04T03:01:28Z | |
| dc.date.conference | 2019-06-30 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/192904 | |
| dc.description.abstractEn | In this article we consider macrocanonical models for texture synthesis. In these models samples are generated given an input texture image and a set of features which should be matched in expectation. It is known that if the images are quantized, macrocanonical models are given by Gibbs measures, using the maximum entropy principle. We study conditions under which this result extends to real-valued images. If these conditions hold, finding a macrocanonical model amounts to minimizing a convex function and sampling from an associated Gibbs measure. We analyze an algorithm which alternates between sampling and minimizing. We present experiments with neural network features and study the drawbacks and advantages of using this sampling scheme. | |
| dc.language.iso | en | |
| dc.subject.en | Texture synthesis | |
| dc.subject.en | Gibbs measure | |
| dc.subject.en | Monte Carlo methods | |
| dc.subject.en | Langevin algorithms | |
| dc.subject.en | Neural networks | |
| dc.title.en | Macrocanonical Models for Texture Synthesis | |
| dc.type | Communication dans un congrès | |
| dc.identifier.doi | 10.1007/978-3-030-22368-7_2 | |
| dc.subject.hal | Statistiques [stat]/Applications [stat.AP] | |
| dc.subject.hal | Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV] | |
| bordeaux.volume | 11603 | |
| 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 | Scale Space and Variational Methods in Computer Vision. SSVM 2019 | |
| bordeaux.country | DE | |
| bordeaux.conference.city | Hofgeismar | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-02093364 | |
| hal.version | 1 | |
| hal.invited | non | |
| hal.proceedings | oui | |
| hal.conference.end | 2019-07-04 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-02093364v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.volume=11603&rft.au=DE%20BORTOLI,%20Valentin&DESOLNEUX,%20Agn%C3%A8s&GALERNE,%20Bruno&LECLAIRE,%20Arthur&rft.genre=unknown |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||