Multi-style image transfer system using conditional cycleGAN

淡江大學機構典藏 > 工學院 > 資訊工程學系暨研究所 > 期刊論文 > Item 987654321/120393

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/120393

题名:	Multi-style image transfer system using conditional cycleGAN
作者:	Tu, Ching-Ting;Lin, Hwei Jen;Tsia, Yihjia
关键词:	Convolutional neural network (CNN);deep learning;generative adversarial net (GAN);conditional GAN (CGAN);CycleGAN;conditional CycleGAN;PatchGAN;image style transfer
日期:	2021-02
上传时间:	2021-03-24 12:10:44 (UTC+8)
出版者:	Taylor & Francis
摘要:	This paper aims to extend the capability of Cycle-Consistent Adversarial Network (CycleGAN) by equipping it with a conditional constraint and extend it into a multi-style image transfer system that can transfer images among more than two image domains. The conditional constraint is given in the form of the target style feature map instead of a one-hot vector, and has shown to provide better transfer results. The proposed system offers greater flexibility for users to choose the style for image transfer. Experimental results show that such an architecture is not only feasible but also yields good results. The proposed architecture can be extended to other transformation applications, such as facial expressions transfer, face aging, and synthesis of various features.
關聯:	The Imaging Science Journal
DOI:	10.1080/13682199.2020.1759977
显示于类别:	[資訊工程學系暨研究所] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	80	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章