Attribute-Driven Spontaneous Motion in Unpaired Image Translation

被引：10
|
作者：
Wu, Ruizheng [1 ]
Tao, Xin [2 ]
Gu, Xiaodong [3 ]
Shen, Xiaoyong [2 ]
Jia, Jiaya [1 ,2 ]
机构：
[1] Chinese Univ Hong Kong, Hong Kong, Peoples R China
[2] Tencent YouTu Lab, Shenzhen, Peoples R China
[3] Harbin Inst Technol, Shenzhen, Peoples R China
来源：
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) | 2019年
关键词：
D O I：
10.1109/ICCV.2019.00602
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Current image translation methods, albeit effective to produce high-quality results in various applications, still do not consider much geometric transform. We in this paper propose the spontaneous motion estimation module, along with a refinement part, to learn attribute-driven deformation between source and target domains. Extensive experiments and visualization demonstrate effectiveness of these modules. We achieve promising results in unpaired-image translation tasks, and enable interesting applications based on spontaneous motion.
引用
下载
收藏
页码：5922 / 5931
页数：10
相关论文
共 50 条
  • [11] A domain translation network with contrastive constraint for unpaired motion image deblurring
    Zhao, Bingxin
    Li, Weihong
    IET IMAGE PROCESSING, 2023, 17 (10) : 2866 - 2880
  • [12] Attribute-Driven Filtering: A new attributes predicting approach for fine-grained image captioning
    Hossen, Md. Bipul
    Ye, Zhongfu
    Abdussalam, Amr
    Ul Hassan, Shabih
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 137
  • [13] SELECTION OF DEVELOPMENT TOOLS BASED ON ATTRIBUTE-DRIVEN DESIGN METHOD
    Qi, Yan
    Mcheick, Hamid
    PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON INTERNET TECHNOLOGIES AND APPLICATIONS (ITA 11), 2011, : 365 - 372
  • [14] Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation
    Noe, Paul-Gauthier
    Mohammadamini, Mohammad
    Matrouf, Driss
    Parcollet, Titouan
    Nautsch, Andreas
    Bonastre, Jean-Francois
    INTERSPEECH 2021, 2021, : 1902 - 1906
  • [15] Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to-Image Generation.
    Wu, Xintian
    Zhao, Hanbin
    Zheng, Liangli
    Ding, Shouhong
    Li, Xi
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, : 1593 - 1602
  • [16] Learning Attribute-driven Disentangled Representations for Interactive Fashion Retrieval
    Hou, Yuxin
    Vig, Eleonora
    Donoser, Michael
    Bazzani, Loris
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 12127 - 12137
  • [17] Partial Attribute-Driven Video Person Re-identification
    Song, Wanru
    Zheng, Jieying
    Wu, Yahong
    Chen, Changhong
    Liu, Feng
    2019 IEEE 31ST INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2019), 2019, : 539 - 546
  • [18] Attribute-Driven Case Notion Discovery for Unlabeled Event Logs
    Lichtenstein, Tom
    Bano, Dorina
    Weske, Mathias
    BUSINESS PROCESS MANAGEMENT WORKSHOPS, BPM 2021, 2022, 436 : 111 - 122
  • [19] Attribute-Driven Hidden Markov Model Trees for Intention Prediction
    Antwarg, Liat
    Rokach, Lior
    Shapira, Bracha
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2012, 42 (06): : 1103 - 1119
  • [20] Face Recognition Algorithm Based on Attribute-Driven Loss Function
    Li Shen
    Su Hansong
    Liu Gaohua
    Wu Huihua
    Wang Meng
    LASER & OPTOELECTRONICS PROGRESS, 2019, 56 (24)
12345