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
中国国家自然科学基金; 国家重点研发计划;
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
收藏
页码:7776 / 7784
页数:9
相关论文
共 50 条
  • [1] A model of facial expression for 3D avatar
    Liu, Zhen
    [J]. COMPUTATIONAL SCIENCE - ICCS 2007, PT 3, PROCEEDINGS, 2007, 4489 : 543 - 546
  • [2] Generation of expression space for realtime facial expression control of 3D avatar
    Kim, Sung-Ho
    [J]. COMPUTER VISION/COMPUTER GRAPHICS COLLABORATION TECHNIQUES, 2007, 4418 : 318 - 329
  • [3] Hybrid On-line 3D Face and Facial Actions Tracking in RGBD Video Sequences
    Pham, Hai X.
    Pavlovic, Vladimir
    [J]. 2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, : 4194 - 4199
  • [4] Real-time face pose tracking and facial expression synthesizing for the animation of 3D avatar
    Chun, Junchul
    Kwon, Ohryun
    Min, Kyongpil
    Park, Peom
    [J]. TECHNOLOGIES FOR E-LEARNING AND DIGITAL ENTERTAINMENT, PROCEEDINGS, 2007, 4469 : 191 - +
  • [5] Learning facial structural dependency in 3D aligned space for face alignment
    Li, Biying
    Liu, Zhiwei
    Wang, Jinqiao
    [J]. IMAGE AND VISION COMPUTING, 2024, 150
  • [6] Stencil-based 3D facial relief creation from RGBD images for 3D printing
    Jung, Soonchul
    Choi, Yoon-Seok
    Kim, Jin-Seo
    [J]. ETRI JOURNAL, 2020, 42 (02) : 272 - 281
  • [7] Accurate and Robust 3D Facial Capture Using a Single RGBD Camera
    Chen, Yen-Lin
    Wu, Hsiang-Tao
    Shi, Fuhao
    Tong, Xin
    Chai, Jinxiang
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2013, : 3615 - 3622
  • [8] Design of Chatbot with 3D Avatar, Voice Interface, and Facial Expression
    Kurniawan, Antonius Angga
    Fachri, Edwin W.
    Elevanita, A.
    Suryadi
    Agushinta, Dewi R.
    [J]. 2015 INTERNATIONAL CONFERENCE ON SCIENCE IN INFORMATION TECHNOLOGY (ICSITECH), 2015, : 326 - 330
  • [9] Statistical models of facial expressions for realistic 3D avatar animation
    Zalewski, L
    Gong, S
    [J]. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2005, : 217 - 222
  • [10] Facial expression generation of 3D avatar based on semantic analysis
    Mukashev, Dinmukhamed
    Kairgaliyev, Merey
    Alibekov, Ulugbek
    Oralbayeva, Nurziya
    Sandygulova, Anara
    [J]. 2021 30TH IEEE INTERNATIONAL CONFERENCE ON ROBOT AND HUMAN INTERACTIVE COMMUNICATION (RO-MAN), 2021, : 89 - 94