3D Morphable Model Parameter Estimation

Estimating the structure of the human face is a long studied and difficult task. In this paper we present a new method for estimating facial structure from only a minimal number of salient feature points. The presented method uses the Extended Kalman Filter (EKF) to regress 3D Morphable Model (3DMM) shape parameters and solve rigid body motion using a simplified camera model. A linear method for initializing the recursive filter is provided. The convergence properties of the method are then evaluated using synthetic data. The method is then demonstrated for both single image shape recovery and shape recovery during tracking.

• Type: Conference
• Year: 2006
• Where: AUSAI
• Authors: Nathan Faggian, Andrew P. Paplinski, Jamie Sherrah
• Keywords: Artificial Intelligence, AUSAI 2006, Extended Kalman Filter, Salient Feature Points, Shape Recovery