Hybrid Integration of Euclidean and Geodesic Distance-Based RBF Interpolation for Facial Animation.

Abstract

Simulating believable facial animation is a topic of increasing interest in computer graphics and visual effects. In this paper we present a hybrid technique for the generation of facial animation based on motion capture data. After capturing a range of facial expressions defined by Facial Action Coding System (FACS), the radial basis function (RBF) is used to transfer the motion data onto two facial models, one realistic and one stylized. The calculations of the distances for the RBF technique are approached in three variants: Euclidean-based, geodesic mesh-based and hybrid-based. The last one takes the advantages of the first two approaches. In order to raise the efficiency, the calculations are aided by preprocessed distance data. The results are then evaluated in a quantitative and qualitative manner, comparing the animation outcomes with the real footage. Our findings show the efficiency of the hybrid technique when generating facial animation with motion capture.