Treffer: Optimal transport between GMM for multiscale texture synthesis
Title:
Optimal transport between GMM for multiscale texture synthesis
Authors:
Contributors:
Mathématiques Appliquées Paris 5 (MAP5 - UMR 8145), Institut National des Sciences Mathématiques et de leurs Interactions - CNRS Mathématiques (INSMI-CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité), CB - Centre Borelli - UMR 9010 (CB), Service de Santé des Armées-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Ecole Normale Supérieure Paris-Saclay (ENS Paris Saclay)-Université Paris Cité (UPCité), Institut de Mathématiques de Bordeaux (IMB), Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS), Luca Calatroni, Marco Donatelli, Serena Morigi, Marco Prato, Giuseppe Rodriguez, Matteo Santacesaria, ANR-19-CE40-0005,MISTIC,Models, Inference and Synthesis for Texture In Color(2019)
Source:
Lecture Notes in Computer ScienceScale Space and Variational Methods in Computer Vision9th International Conference, SSVM 2023, Santa Margherita di Pula, Italy, May 21–25, 2023, Proceedings ; International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) ; https://hal.science/hal-03613622 ; 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⟩
Publisher Information:
CCSD
Springer
Springer
Publication Year:
2023
Subject Terms:
Document Type:
Konferenz
conference object
Language:
English
DOI:
10.1007/978-3-031-31975-4_48
Availability:
Rights:
info:eu-repo/semantics/OpenAccess
Accession Number:
edsbas.591F8545
Database:
BASE
Weitere Informationen
International audience ; 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.