RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes

被引:95
|
作者
Wu, Po-Wei [1 ]
Lin, Yu-Jing [1 ]
Chang, Che-Han [2 ]
Chang, Edward Y. [2 ,3 ]
Liao, Shih-Wei [1 ]
机构
[1] Natl Taiwan Univ, Taipei, Taiwan
[2] HTC Res & Healthcare, Taipei, Taiwan
[3] Stanford Univ, Stanford, CA 94305 USA
关键词
D O I
10.1109/ICCV.2019.00601
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multi-domain image-to-image translation has gained increasing attention recently. Previous methods take an image and some target attributes as inputs and generate an output image with the desired attributes. However, such methods have two limitations. First, these methods assume binary-valued attributes and thus cannot yield satisfactory results for fine-grained control. Second, these methods require specifying the entire set of target attributes, even if most of the attributes would not be changed. To address these limitations, we propose RelGAN, a new method for multi-domain image-to-image translation. The key idea is to use relative attributes, which describes the desired change on selected attributes. Our method is capable of modifying images by changing particular attributes of interest in a continuous manner while preserving the other attributes. Experimental results demonstrate both the quantitative and qualitative effectiveness of our method on the tasks of facial attribute transfer and interpolation.
引用
收藏
页码:5913 / 5921
页数:9
相关论文
共 50 条
  • [31] Zero-shot unsupervised image-to-image translation via exploiting semantic attributes
    Chen, Yuanqi
    Yu, Xiaoming
    Liu, Shan
    Gao, Wei
    Li, Ge
    IMAGE AND VISION COMPUTING, 2022, 124
  • [32] MDT: UNSUPERVISED MULTI-DOMAIN IMAGE-TO-IMAGE TRANSLATOR BASED ON GENERATIVE ADVERSARIAL NETWORKS
    Lin, Ye
    Fu, Keren
    Ling, Shenggui
    Cheng, Peng
    2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 598 - 602
  • [33] Unsupervised multi-domain image translation with domain representation learning
    Liu, Huajun
    Chen, Lei
    Sui, Haigang
    Zhu, Qing
    Lei, Dian
    Liu, Shubo
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2021, 99
  • [34] Image-to-image translation for cross-domain disentanglement
    Gonzalez-Garcia, Abel
    van de Weijer, Joost
    Bengio, Yoshua
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [35] AU-GAN: Attention U-Net Based on a Built-In Attention for Multi-domain Image-to-Image Translation
    Xu, Caie
    Gan, Jin
    Wu, Mingyang
    Ni, Dandan
    WEB AND BIG DATA. APWEB-WAIM 2022 INTERNATIONAL WORKSHOPS, KGMA 2022, SEMIBDMA 2022, DEEPLUDA 2022, 2023, 1784 : 202 - 218
  • [36] Probabilistic Plant Modeling via Multi-View Image-to-Image Translation
    Isokane, Takahiro
    Okura, Fumio
    Ide, Ayaka
    Matsushita, Yasuyuki
    Yagi, Yasushi
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 2906 - 2915
  • [37] Gated SwitchGAN for Multi-Domain Facial Image Translation
    Zhang, Xiaokang
    Zhu, Yuanlue
    Chen, Wenting
    Liu, Wenshuang
    Shen, Linlin
    IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 24 : 1990 - 2003
  • [38] Underwater Image Dehazing via Unpaired Image-to-image Translation
    Cho, Younggun
    Jang, Hyesu
    Malav, Ramavtar
    Pandey, Gaurav
    Kim, Ayoung
    INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, 2020, 18 (03) : 605 - 614
  • [39] Underwater Image Dehazing via Unpaired Image-to-image Translation
    Younggun Cho
    Hyesu Jang
    Ramavtar Malav
    Gaurav Pandey
    Ayoung Kim
    International Journal of Control, Automation and Systems, 2020, 18 : 605 - 614
  • [40] Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation
    Arar, Moab
    Ginger, Yiftach
    Danon, Dov
    Bermano, Amit H.
    Cohen-Or, Daniel
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, : 13407 - 13416