教師資料查詢 | 類別: 期刊論文 | 教師: 林慧珍 Lin Hwei-jen (瀏覽個人網頁)

標題:MultipleStyle 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MultipleStyle Image Transfer System Using Conditional CycleGAN
作品名稱(其他語言)
著者Hwei Jen Lin; Ching-Ting Tu; Yihjia Tsia; Fu-Wen Yang
單位
出版者
著錄名稱、卷期、頁數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
語言中文
ISSN1368-2199
期刊性質國內
收錄於SCI;
產學合作
通訊作者
審稿制度
國別中華民國
公開徵稿
出版型式,電子版
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!