Versatile Face Animator: Driving Arbitrary 3D Facial Avatar in RGBD Space

被引:2
|
作者
Wang, Haoyu [1 ]
Wu, Haozhe [1 ]
Xing, Junliang [1 ]
Jia, Jia [2 ]
机构
[1] Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Dept Comp Sci & Technol, Beijing Natl Res Ctr Informat Sci & Technol, Beijing 100084, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
3D facial animation; Motion capture; Motion retargeting;
D O I
10.1145/3581783.3612065
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Creating realistic 3D facial animation is crucial for various applications in the movie production and gaming industry, especially with the burgeoning demand in the metaverse. However, prevalent methods such as blendshape-based approaches and facial rigging techniques are time-consuming, labor-intensive, and lack standardized configurations, making facial animation production challenging and costly. In this paper, we propose a novel self-supervised framework, Versatile Face Animator, which combines facial motion capture with motion retargeting in an end-to-end manner, eliminating the need for blendshapes or rigs. Our method has the following two main characteristics: 1) we propose an RGBD animation module to learn facial motion from raw RGBD videos by hierarchical motion dictionaries and animate RGBD images rendered from 3D facial mesh coarse-to-fine, enabling facial animation on arbitrary 3D characters regardless of their topology, textures, blendshapes, and rigs; and 2) we introduce a mesh retarget module to utilize RGBD animation to create 3D facial animation by manipulating facial mesh with controller transformations, which are estimated from dense optical flow fields and blended together with geodesic-distance-based weights. Comprehensive experiments demonstrate the effectiveness of our proposed framework in generating impressive 3D facial animation results, highlighting its potential as a promising solution for the cost-effective and efficient production of facial animation in the metaverse.
引用
下载
收藏
页码:7776 / 7784
页数:9
相关论文
共 50 条
  • [21] A Two-Stage Framework for 3D Face Reconstruction from RGBD Images
    Wang, Kangkan
    Wang, Xianwang
    Pan, Zhigeng
    Liu, Kai
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2014, 36 (08) : 1493 - 1504
  • [22] Animatomy: an Animator-centric, Anatomically Inspired System for 3D Facial Modeling, Animation and Transfer
    Choi, Byungkuk
    Eom, Haekwang
    Mouscadet, Benjamin
    Cullingford, Stephen
    Ma, Kurt
    Gassel, Stefanie
    Kim, Suzi
    Moffat, Andrew
    PROCEEDINGS SIGGRAPH ASIA 2022, 2022,
  • [23] Noise versus facial expression on 3D face recognition
    Queirolo, Chaua
    Segundo, Mauricio P.
    Bellon, Olga
    Silva, Luciano
    14TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS, 2007, : 171 - +
  • [24] Capturing subtle facial motions in 3D face tracking
    Wen, Z
    Huang, TS
    NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, 2003, : 1343 - 1350
  • [25] Local or global 3D face and facial feature tracker
    Zepeda, Jose Alonso Ybanez
    Davoine, Franck
    Charbit, Maurice
    2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7, 2007, : 505 - +
  • [26] A method of face recognition using 3D facial surfaces
    B. A. Echeagaray-Patrón
    V. I. Kober
    V. N. Karnaukhov
    V. V. Kuznetsov
    Journal of Communications Technology and Electronics, 2017, 62 : 648 - 652
  • [27] A Method of Face Recognition Using 3D Facial Surfaces
    Echeagaray-Patron, B. A.
    Kober, V. I.
    Karnaukhov, V. N.
    Kuznetsov, V. V.
    JOURNAL OF COMMUNICATIONS TECHNOLOGY AND ELECTRONICS, 2017, 62 (06) : 648 - 652
  • [28] Real time 3D face and facial feature tracking
    Fadi Dornaika
    Javier Orozco
    Journal of Real-Time Image Processing, 2007, 2 : 35 - 44
  • [29] 3D face recognition based on matching of facial surfaces
    Adriana Echeagaray-Patron, Beatriz
    Kober, Vitaly
    OPTICS AND PHOTONICS FOR INFORMATION PROCESSING IX, 2015, 9598
  • [30] Face Video Deblurring using 3D Facial Priors
    Ren, Wenqi
    Yang, Jiaolong
    Deng, Senyou
    Wipf, David
    Cao, Xiaochun
    Tong, Xin
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 9387 - 9396