Learning to Caricature via Semantic Shape Transform

被引:8
|
作者
Chu, Wenqing [1 ,4 ]
Hung, Wei-Chih [2 ]
Tsai, Yi-Hsuan [3 ]
Chang, Yu-Ting [2 ]
Li, Yijun [5 ]
Cai, Deng [1 ]
Yang, Ming-Hsuan [2 ,6 ]
机构
[1] Zhejiang Univ, State Key Lab CAD&CG, Hangzhou, Zhejiang, Peoples R China
[2] Univ Calif Merced, Elect Engn & Comp Sci, Merced, CA USA
[3] NEC Labs Amer, Santa Clara, CA USA
[4] Tencent Youtu Lab, Shanghai, Peoples R China
[5] Adobe Res, San Jose, CA USA
[6] Yonsei Univ, Seoul, South Korea
基金
美国国家科学基金会;
关键词
Caricature generation; Dense shape transformation; Semantic map; FACES;
D O I
10.1007/s11263-021-01489-1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Caricature is an artistic drawing created to abstract or exaggerate facial features of a person. Rendering visually pleasing caricatures is a difficult task that requires professional skills, and thus it is of great interest to design a method to automatically generate such drawings. To deal with large shape changes, we propose an algorithm based on a semantic shape transform to produce diverse and plausible shape exaggerations. Specifically, we predict pixel-wise semantic correspondences and perform image warping on the input photo to achieve dense shape transformation. We show that the proposed framework is able to render visually pleasing shape exaggerations while maintaining their facial structures. In addition, our model allows users to manipulate the shape via the semantic map. We demonstrate the effectiveness of our approach on a large photograph-caricature benchmark dataset with comparisons to the state-of-the-art methods.
引用
收藏
页码:2663 / 2679
页数:17
相关论文
共 50 条
  • [1] Learning to Caricature via Semantic Shape Transform
    Wenqing Chu
    Wei-Chih Hung
    Yi-Hsuan Tsai
    Yu-Ting Chang
    Yijun Li
    Deng Cai
    Ming-Hsuan Yang
    International Journal of Computer Vision, 2021, 129 : 2663 - 2679
  • [2] Learning semantic abstraction of shape via 3D region of interest
    Fang, Haiyue
    Wang, Xiaogang
    Cai, Zheyuan
    Shi, Yahao
    Sun, Xun
    Wu, Shilin
    Zhou, Bin
    GRAPHICAL MODELS, 2019, 105
  • [3] Shape registration via the wavelet transform
    Chalfant, Julie S.
    Patrikalakis, Nicholas M.
    IEEE INTERNATIONAL CONFERENCE ON SHAPE MODELING AND APPLICATIONS 2008, PROCEEDINGS, 2008, : 277 - 278
  • [4] Face shape transfer via semantic warping
    Zonglin Li
    Xiaoqian Lv
    Wei Yu
    Qinglin Liu
    Jingbo Lin
    Shengping Zhang
    Visual Intelligence, 2 (1):
  • [5] Impulse Denoising via Transform Learning
    Maggu, Jyoti
    Hussein, Ramy
    Majumdar, Angshul
    Ward, Rabab
    2017 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2017), 2017, : 1250 - 1254
  • [6] Learning Semantic Hierarchies via Word Embeddings
    Fu, Ruiji
    Guo, Jiang
    Qin, Bing
    Che, Wanxiang
    Wang, Haifeng
    Liu, Ting
    PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2014, : 1199 - 1209
  • [7] Image Search Via Semantic Hashing Learning
    Sun, Weicheng
    Zhu, Songhao
    Cheng, Yanyun
    2017 29TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC), 2017, : 1986 - 1990
  • [8] Semantic Image Synthesis via Adversarial Learning
    Dong, Hao
    Yu, Simiao
    Wu, Chao
    Guo, Yike
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : CP1 - CP38
  • [9] Shape from semantic segmentation via the geometric Renyi divergence
    Koizumi, Tatsuro
    Smith, William A. P.
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021, 2021, : 2311 - 2320
  • [10] Shape Part Transfer via Semantic Latent Space Factorization
    Groscot, Raphael
    Cohen, Laurent
    Guibas, Leonidas
    GEOMETRIC SCIENCE OF INFORMATION, 2019, 11712 : 511 - 519