A Style-Based Caricature Generator

被引:3
|
作者
Laishram, Lamyanba [1 ]
Shaheryar, Muhammad [1 ]
Lee, Jong Taek [1 ]
Jung, Soon Ki [1 ]
机构
[1] Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu, South Korea
来源
关键词
Caricature; Style Generator; Generative Adversarial Network; FACES;
D O I
10.1007/978-981-99-4914-4_6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A facial caricature is a creation of new artistic and exaggerated faces which translates into a real image to convey sarcasm or humor while keeping the identity of the subject. In this work, we proposed a new way to create caricatures by exaggerating facial features like the eyes and mouth while keeping the facial contour intact and a realistic style. Our method can be categorized into two steps. First, the facial exaggeration process transformed faces into caricature face images while maintaining facial contours. Second, the appearance style generator is trained in unpaired using the generated caricature faces to produce a facial caricature that can change to any realistic style of our preference. Experimental results show our model produces more realistic and disentangled caricature images as compared to some of the previous methods. Our method can also generate caricature images from real images.
引用
收藏
页码:71 / 82
页数:12
相关论文
共 50 条
  • [1] A Style-Based Generator Architecture for Generative Adversarial Networks
    Karras, Tero
    Laine, Samuli
    Aila, Timo
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (12) : 4217 - 4228
  • [2] Style-Based Tree GAN for Point Cloud Generator
    Shen, Yang
    Xu, Hao
    Bao, Yanxia
    Xu, Zhengnan
    Gu, Yuanhu
    Lu, Jiang
    Ying, Zhen
    Lou, Kenan
    [J]. IEEE ACCESS, 2024, 12 : 27017 - 27028
  • [3] A Style-Based Generator Architecture for Generative Adversarial Networks
    Karras, Tero
    Laine, Samuli
    Aila, Timo
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 4396 - 4405
  • [4] StyleSwap: Style-Based Generator Empowers Robust Face Swapping
    Xu, Zhiliang
    Zhou, Hang
    Hong, Zhibin
    Liu, Ziwei
    Liu, Jiaming
    Guo, Zhizhi
    Han, Junyu
    Liu, Jingtuo
    Ding, Errui
    Wang, Jingdong
    [J]. COMPUTER VISION - ECCV 2022, PT XIV, 2022, 13674 : 661 - 677
  • [5] Style-based Point Generator with Adversarial Rendering for Point Cloud Completion
    Xie, Chulin
    Wang, Chuxin
    Zhang, Bo
    Yang, Hao
    Chen, Dong
    Wen, Fang
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 4617 - 4626
  • [6] Style-based motion synthesis
    Urtasun, R
    Glardon, P
    Boulic, R
    Thalmann, D
    Fua, P
    [J]. COMPUTER GRAPHICS FORUM, 2004, 23 (04) : 799 - 812
  • [7] Style-Based Outfit Recommendation
    De Divitiis, Lavinia
    Becattini, Federico
    Baecchi, Claudio
    Del Bimbo, Alberto
    [J]. 2021 INTERNATIONAL CONFERENCE ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI), 2021, : 1 - 4
  • [8] Style-based motion editing
    Jia, Lingtao
    Yang, Yuedong
    Tang, Shaopeng
    Hao, Aimin
    [J]. SECOND WORKSHOP ON DIGITAL MEDIA AND ITS APPLICATION IN MUSEUM & HERITAGE, PROCEEDINGS, 2007, : 129 - 134
  • [9] STYLE-BASED ARCHITECTURAL RECONFIGURATIONS
    Bruni, Roberto
    Lafuente, Alberto Lluch
    Montanari, Ugo
    Tuosto, Emilio
    [J]. BULLETIN OF THE EUROPEAN ASSOCIATION FOR THEORETICAL COMPUTER SCIENCE, 2008, (94): : 161 - 180
  • [10] Style-based inverse kinematics
    Grochow, K
    Martin, SL
    Hertzmann, A
    Popovic, Z
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2004, 23 (03): : 522 - 531