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
  • [1] Multi-Domain Image-to-Image Translation via a Unified Circular Framework
    Wang, Yuxi
    Zhang, Zhaoxiang
    Hao, Wangli
    Song, Chunfeng
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 : 670 - 684
  • [2] DMDIT: Diverse multi-domain image-to-image translation
    Shao, Mingwen
    Zhang, Youcai
    Liu, Huan
    Wang, Chao
    Li, Le
    Shao, Xun
    KNOWLEDGE-BASED SYSTEMS, 2021, 229
  • [3] Retrieval Guided Unsupervised Multi-domain Image-to-Image Translation
    Gomez, Raul
    Liu, Yahui
    De Nadai, Marco
    Karatzas, Dimosthenis
    Lepri, Bruno
    Sebe, Nicu
    MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, : 3164 - 3172
  • [4] Multi-Domain Image-to-Image Translation with Adaptive Inference Graph
    The-Phuc Nguyen
    Lathuiliere, Stephane
    Ricci, Elisa
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 5368 - 5375
  • [5] Registration on DCE-MRI images via multi-domain image-to-image translation
    Cai, Naxin
    Chen, Houjin
    Li, Yanfeng
    Peng, Yahui
    Guo, Linqiang
    COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2023, 104
  • [6] MULTI-DOMAIN UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION WITH APPEARANCE ADAPTIVE CONVOLUTION
    Jeong, Somi
    Lee, Jiyoung
    Sohn, Kwanghoon
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 1750 - 1754
  • [7] Cross-Granularity Learning for Multi-Domain Image-to-Image Translation
    Fu, Huiyuan
    Yu, Ting
    Wang, Xin
    Ma, Huadong
    MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, : 3099 - 3107
  • [8] Self-attention StarGAN for Multi-domain Image-to-Image Translation
    He, Ziliang
    Yang, Zhenguo
    Mao, Xudong
    Lv, Jianming
    Li, Qing
    Liu, Wenyin
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: IMAGE PROCESSING, PT III, 2019, 11729 : 537 - 549
  • [9] StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
    Choi, Yunjey
    Choi, Minje
    Kim, Munyoung
    Ha, Jung-Woo
    Kim, Sunghun
    Choo, Jaegul
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 8789 - 8797
  • [10] GD-StarGAN: Multi-domain image-to-image translation in garment design
    Shen, Yangyun
    Huang, Runnan
    Huang, Wenkai
    PLOS ONE, 2020, 15 (04):