An Approach to Face Warping via Motion Data Acquired from Kinect Sensors

This paper proposes a novel approach to face warping based on the motion data captured by Kinect sensor. First, the user’s face as well as the face motion is recorded in a natural environment using Kinect sensor. Second, we perform facial motion retargeting using Radial Basis Function (RBF) interpolation. Finally, we propose a face warping approach to deforming a 3D face model by geodesic RBF. Experimental results show the efficiency of the proposed approach.