A Two-Step Approach for Interactive Animatable Avatars

被引:0
|
作者
Kitamura, Takumi [2 ]
Iwamoto, Naoya [2 ]
Kawasaki, Hiroshi [1 ]
Thomas, Diego [1 ]
机构
[1] Kyushu Univ, Fukuoka, Japan
[2] Huawei Technol Japan KK, Tokyo, Japan
关键词
Animatable avatars; Real time; Clothes animation; Non-rigid fitting;
D O I
10.1007/978-3-031-50072-5_39
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a two-step human body animation technique that generates pose-dependent detailed deformations in real-time on standard animation pipeline. In order to accomplish real-time animation, we utilize the template-based approach and represent pose-dependent deformations using 2D displacement maps. In order to generalize to totally new motions, we employ a two-step strategy: 1) the first step aligns the topology of the Skinned Multi-Person Linear Model (SMPL) [25] model to our proposed template model. 2) the second step models detailed clothes and muscles deformation for the specific motion. Our experimental results show that our proposed method can animate an avatar up to 30 times faster than baselines while keeping similar or even better level of details.
引用
收藏
页码:491 / 509
页数:19
相关论文
共 50 条
  • [1] A two-step interactive review process
    Park, C. W.
    [J]. JOURNAL OF CONSUMER PSYCHOLOGY, 2010, 20 (02) : 105 - 106
  • [2] Two-step approach
    Buergin-Wolff, A.
    Hadziselimovic, Faruk
    [J]. DEUTSCHES ARZTEBLATT INTERNATIONAL, 2014, 111 (12):
  • [3] Two-step approach Reply
    Zimmer, Klaus-Peter
    Schuppan, Detlef
    [J]. DEUTSCHES ARZTEBLATT INTERNATIONAL, 2014, 111 (12):
  • [4] A two-step approach for interactive pre-integrated volume rendering of unstructured grids
    Roettger, S
    Ertl, T
    [J]. IEEE/ACM SIGGRAPH SYMPOSIUM ON VOLUME VISUALIZATION AND GRAPHICS 2002, PROCEEDINGS, 2002, : 23 - 28
  • [5] A two-step approach to optimizing meshes
    Ma, Xin
    Wei, Mingqiang
    Wu, Jianhuang
    Wang, Shuguo
    Fu, Yili
    [J]. 2010 INTERNATIONAL CONFERENCE ON BIO-INSPIRED SYSTEMS AND SIGNAL PROCESSING (ICBSSP 2010), 2010, : 25 - 30
  • [6] A two-step adaptive beamforming approach
    Zhang, RF
    Liu, ZW
    Zhou, L
    Ke, Y
    [J]. ICR '96 - 1996 CIE INTERNATIONAL CONFERENCE OF RADAR, PROCEEDINGS, 1996, : 397 - 400
  • [7] Relightable and Animatable Neural Avatars from Videos
    Lin, Wenbin
    Zheng, Chengwei
    Yong, Jun-Hai
    Xu, Feng
    [J]. THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 4, 2024, : 3486 - 3494
  • [8] Progress in testing the interactive two-step model of lexical access
    Schwartz, MF
    [J]. BRAIN AND LANGUAGE, 2004, 91 (01) : 68 - 68
  • [9] FLARE: Fast Learning of Animatable and Relightable Mesh Avatars
    Bharadwaj, Shrisha
    Zheng, Yufeng
    Hilliges, Otmar
    Black, Michael J.
    Abrevaya, Victoria Fernandez
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2023, 42 (06):
  • [10] GANHead: Towards Generative Animatable Neural Head Avatars
    Wu, Sijing
    Yan, Yichao
    Li, Yunhao
    Cheng, Yuhao
    Zhu, Wenhan
    Gao, Ke
    Li, Xiaobo
    Zhai, Guangtao
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 437 - 447