Optimal transport between GMM for multiscale texture synthesis
Langue
en
Communication dans un congrès
Ce document a été publié dans
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, 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), 2023-05-21, Cagliari.
Springer
Résumé en anglais
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 ...Lire la suite >
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.< Réduire
Mots clés en anglais
Optimal transport
Gaussian mixture models
Texture synthesis
Origine
Importé de halUnités de recherche