Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

被引:10458
|
作者
Zhu, Jun-Yan [1 ]
Park, Taesung [1 ]
Isola, Phillip [1 ]
Efros, Alexei A. [1 ]
机构
[1] Univ Calif Berkeley, Berkeley AI Res BAIR Lab, Berkeley, CA 94720 USA
基金
美国国家科学基金会;
关键词
D O I
10.1109/ICCV.2017.244
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples. Our goal is to learn a mapping G : X -> Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping F : Y -> X and introduce a cycle consistency loss to push F(G(X)) approximate to X (and vice versa). Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach.
引用
收藏
页码:2242 / 2251
页数:10
相关论文
共 50 条
  • [1] Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks
    Li, Minjun
    Huang, Haozhi
    Ma, Lin
    Liu, Wei
    Zhang, Tong
    Jiang, Yugang
    [J]. COMPUTER VISION - ECCV 2018, PT IX, 2018, 11213 : 186 - 201
  • [2] Unsupervised image-to-image translation via long-short cycle-consistent adversarial networks
    Gang Wang
    Haibo Shi
    Yufei Chen
    Bin Wu
    [J]. Applied Intelligence, 2023, 53 : 17243 - 17259
  • [3] Unsupervised image-to-image translation via long-short cycle-consistent adversarial networks
    Wang, Gang
    Shi, Haibo
    Chen, Yufei
    Wu, Bin
    [J]. APPLIED INTELLIGENCE, 2023, 53 (14) : 17243 - 17259
  • [4] UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation
    Torbunov, Dmitrii
    Huang, Yi
    Yu, Haiwang
    Huang, Jin
    Yoo, Shinjae
    Lin, Meifeng
    Viren, Brett
    Ren, Yihui
    [J]. 2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 702 - 712
  • [5] Image-to-image Translation Based on Improved Cycle-consistent Generative Adversarial Network
    Zhang Jinglei
    Hou Yawei
    [J]. JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2020, 42 (05) : 1216 - 1222
  • [6] An Extensive Study of Cycle-Consistent Generative Networks for Image-to-Image Translation
    Liu, Yu
    Guo, Yanming
    Chen, Wei
    Lew, Michael S.
    [J]. 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 219 - 224
  • [7] SAR-to-Optical Image Translation Using Supervised Cycle-Consistent Adversarial Networks
    Wang, Lei
    Xu, Xin
    Yu, Yue
    Yang, Rui
    Gui, Rong
    Xu, Zhaozhuo
    Pu, Fangling
    [J]. IEEE ACCESS, 2019, 7 : 129136 - 129149
  • [8] AttentionGAN: Unpaired Image-to-Image Translation Using Attention-Guided Generative Adversarial Networks
    Tang, Hao
    Liu, Hong
    Xu, Dan
    Torr, Philip H. S.
    Sebe, Nicu
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (04) : 1972 - 1987
  • [9] Improving Generative Adversarial Networks for Patch-Based Unpaired Image-to-Image Translation
    Boehland, Moritz
    Bruch, Roman
    Baeuerle, Simon
    Rettenberger, Luca
    Reischl, Markus
    [J]. IEEE ACCESS, 2023, 11 : 127895 - 127906
  • [10] Asynchronous Generative Adversarial Network for Asymmetric Unpaired Image-to-Image Translation
    Zheng, Ziqiang
    Bin, Yi
    Lv, Xiaoou
    Wu, Yang
    Yang, Yang
    Shen, Heng Tao
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 2474 - 2487