Multi-style image transfer system using conditional cycleGAN
學年 109
學期 2
出版(發表)日期 2021-02-01
作品名稱 Multi-style image transfer system using conditional cycleGAN
著者 Tu, Ching-Ting; Lin, Hwei Jen; Tsia, Yihjia
著錄名稱、卷期、頁數 The Imaging Science Journal
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.
關鍵字 Convolutional neural network (CNN);deep learning;generative adversarial net (GAN);conditional GAN (CGAN);CycleGAN;conditional CycleGAN;PatchGAN;image style transfer
語言 en_US
ISSN 1368-2199
期刊性質 國外
國別 GBR
出版型式 ,電子版,紙本

機構典藏連結 ( )