Optimal transport between GMM for multiscale texture synthesis
Idioma
en
Communication dans un congrès
Este ítem está publicado en
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
Resumen en inglés
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 ...Leer más >
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.< Leer menos
Palabras clave en inglés
Optimal transport
Gaussian mixture models
Texture synthesis
Orígen
Importado de HalCentros de investigación