A Novel Wasserstein Quaternion Generative Adversarial Network for Color Image Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jia, Zhigang, Wang, Duan, Wang, Hengkai, Xie, Yajun, Zhao, Meixiang, Zhao, Xiaoyu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908701626990592
author Jia, Zhigang
Wang, Duan
Wang, Hengkai
Xie, Yajun
Zhao, Meixiang
Zhao, Xiaoyu
author_facet Jia, Zhigang
Wang, Duan
Wang, Hengkai
Xie, Yajun
Zhao, Meixiang
Zhao, Xiaoyu
contents Color image generation has a wide range of applications, but the existing generation models ignore the correlation among color channels, which may lead to chromatic aberration problems. In addition, the data distribution problem of color images has not been systematically elaborated and explained, so that there is still the lack of the theory about measuring different color images datasets. In this paper, we define a new quaternion Wasserstein distance and develop its dual theory. To deal with the quaternion linear programming problem, we derive the strong duality form with helps of quaternion convex set separation theorem and quaternion Farkas lemma. With using quaternion Wasserstein distance, we propose a novel Wasserstein quaternion generative adversarial network. Experiments demonstrate that this novel model surpasses both the (quaternion) generative adversarial networks and the Wasserstein generative adversarial network in terms of generation efficiency and image quality.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08542
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Novel Wasserstein Quaternion Generative Adversarial Network for Color Image Generation
Jia, Zhigang
Wang, Duan
Wang, Hengkai
Xie, Yajun
Zhao, Meixiang
Zhao, Xiaoyu
Computer Vision and Pattern Recognition
Artificial Intelligence
Numerical Analysis
Color image generation has a wide range of applications, but the existing generation models ignore the correlation among color channels, which may lead to chromatic aberration problems. In addition, the data distribution problem of color images has not been systematically elaborated and explained, so that there is still the lack of the theory about measuring different color images datasets. In this paper, we define a new quaternion Wasserstein distance and develop its dual theory. To deal with the quaternion linear programming problem, we derive the strong duality form with helps of quaternion convex set separation theorem and quaternion Farkas lemma. With using quaternion Wasserstein distance, we propose a novel Wasserstein quaternion generative adversarial network. Experiments demonstrate that this novel model surpasses both the (quaternion) generative adversarial networks and the Wasserstein generative adversarial network in terms of generation efficiency and image quality.
title A Novel Wasserstein Quaternion Generative Adversarial Network for Color Image Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Numerical Analysis
url https://arxiv.org/abs/2512.08542