English  |  正體中文  |  简体中文  |  Items with full text/Total items : 58286/91808 (63%)
Visitors : 13821677      Online Users : 81
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/120393


    Title: Multi-style image transfer system using conditional cycleGAN
    Authors: Tu, Ching-Ting;Lin, Hwei Jen;Tsia, Yihjia
    Keywords: Convolutional neural network (CNN);deep learning;generative adversarial net (GAN);conditional GAN (CGAN);CycleGAN;conditional CycleGAN;PatchGAN;image style transfer
    Date: 2021-02
    Issue Date: 2021-03-24 12:10:44 (UTC+8)
    Publisher: Taylor & Francis
    Abstract: 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.
    Relation: The Imaging Science Journal
    DOI: 10.1080/13682199.2020.1759977
    Appears in Collections:[Graduate Institute & Department of Computer Science and Information Engineering] Journal Article

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML8View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback