Geometry-driven photorealistic facial expression synthesis

  • Authors:
  • Qingshan Zhang;Zicheng Liu;Baining Guo;Harry Shum

  • Affiliations:
  • Microsoft Research Asia, Beijing, China;Microsoft Research, Redmond, WA;Microsoft Research Asia, Beijing, China;Microsoft Research Asia, Beijing, China

  • Venue:
  • Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Expression mapping (also called performance driven animation) has been a popular method to generate facial animations. One shortcoming of this method is that it does not generate expression details such as the wrinkles due to the skin deformation. In this paper, we provide a solution to this problem. We have developed a geometry-driven facial expression synthesis system. Given the feature point positions (geometry) of a facial expression, our system automatically synthesizes the corresponding expression image which has photorealistic and natural looking expression details. Since the number of feature points required by the synthesis system is in general more than what is available from the performer due to the difficulty of tracking, we have developed a technique to infer the feature point motions from a subset by using an example-based approach. Another application of our system is on expression editing where the user drags the feature points while the system interactively generates facial expressions with skin deformation details.