Realistic 3D Facial Animation

(c) CAIG Lab, NCTU

　

Description
From the aspect of facial animation, motion capture is a convincing approach for data acquisition. Current facial motion capture devices can only track markers or feature points on a face. They are difficult to handle facial details, such as wrinkles or dimples. In this project, we plan to improve facial detail capture method. After analyzing the correlations between feature points and facial details, a feature-point-driven facial motion model with detail expressions can improve the drawback of current performance-driven facial animation.

Current Results
Facial Animation Diven by Mocap Data


Enhancement with wrinkles

Publications
Journal Papers:
  • I-Chen Lin, Wen-Hsing Chang, Yung-Sheng Lo, Jen-Yu Peng, Chan-Yu Lin, "Image-based Detail Reconstruction of Non-Lambertian Surfaces", Computer Animation and Virtual Worlds, 21(1):55-68, Jan.-Feb., 2010.
    Download: CAVW10_Draft.pdf (about 2.1MB) video (about 25.6MB) (Please download the officially published version from the Wiley InterScience)

  • Jia-Ru Lin, I-Chen Lin, "Multi-layered Expression Synthesis", accepted by Journal of Information Science and Engineering, 2009.


  • I-Chen Lin, Ming Ouhyoung, “Mirror Mocap: Automatic and Efficient Capture of Dense 3D Facial Motion Parameters from Video”, The Visual Computer, 12(6): 355-372, July, 2005.
    Download: TVC05.pdf (about 3.6MB), project page (Please download the officially published version from the Springer digital library)


International Conference Papers:

  • Yung-Sheng Lo, I-Chen Lin, Wen-Xing Zhang, Wen-Chih Tai, Shian-Jun Chiou, "Capturing Facial Details by Space-time Shape-from-shading", Proc. Computer Graphics International (CGI'08), pp.118-125, Istanbul, Turkey, June 2008.
    Download: CGI08.pdf (about 712KB)

  • Chii-Yuan Chuang, I-Chen Lin, Yung-Sheng Lo, Chao-Chih Lin
    "Feature-point Driven 3D Expression Editing"
    Proc. Intl. Conf. on Computer Graphics Theory and Applications GRAPP' 07, pp.165-170, Barcelona, Spain, Mar. 2007.

　

Project Support
This research is partially supported by:
  • NSC 95-2221-E-009 -164 -MY3: "A Study on Motion Synthesis of Body and Facial Animation for Human Characters", 2006/08~2009/07.
  • NSC 94-2213-E-009-151: "Extracting and Synthesizing Detailed Expressions for Realistic 3D Facial Animation", 2005/08~2006/07.