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
  • [41] Multi-cropping contrastive learning and domain consistency for unsupervised image-to-image translation
    Zhao, Chen
    Cai, Wei-Ling
    Yuan, Zheng
    Hu, Cheng-Wei
    IET IMAGE PROCESSING, 2025, 19 (01)
  • [42] Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptation
    Pizzati, Fabio
    de Charette, Raoul
    Zaccaria, Michela
    Cerri, Pietro
    2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2020, : 2979 - 2987
  • [43] CoPrGAN: Image-to-Image Translation via Content Preservation
    Yu, Xiaoming
    Zhou, Gan
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT III, 2022, 13531 : 37 - 49
  • [44] Diverse Image-to-Image Translation via Disentangled Representations
    Lee, Hsin-Ying
    Tseng, Hung-Yu
    Huang, Jia-Bin
    Singh, Maneesh
    Yang, Ming-Hsuan
    COMPUTER VISION - ECCV 2018, PT I, 2018, 11205 : 36 - 52
  • [45] Image-to-image Translation via Hierarchical Style Disentanglement
    Li, Xinyang
    Zhang, Shengchuan
    Hu, Jie
    Cao, Liujuan
    Hong, Xiaopeng
    Mao, Xudong
    Huang, Feiyue
    Wu, Yongjian
    Ji, Rongrong
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 8635 - 8644
  • [46] Message Drives Image: A Coverless Image Steganography Framework Using Multi-Domain Image Translation
    Xue, Rui
    Wang, Yaning
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [47] Unsupervised Exemplar-Domain Aware Image-to-Image Translation
    Fu, Yuanbin
    Ma, Jiayi
    Guo, Xiaojie
    ENTROPY, 2021, 23 (05)
  • [48] Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation
    Brehm, Stephan
    Scherer, Sebastian
    Lienhart, Rainer
    ICAART: PROCEEDINGS OF THE 14TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 2, 2022, : 131 - 141
  • [49] Cross-Domain Interpolation for Unpaired Image-to-Image Translation
    Lopez, Jorge
    Mauricio, Antoni
    Diaz, Jose
    Camara, Guillermo
    COMPUTER VISION SYSTEMS (ICVS 2019), 2019, 11754 : 542 - 551
  • [50] ResAttr-GAN: Unpaired Deep Residual Attributes Learning for Multi-Domain Face Image Translation
    Tao, Rentuo
    Li, Ziqiang
    Tao, Renshuai
    Li, Bin
    IEEE ACCESS, 2019, 7 : 132594 - 132608