Automatic and real-time 3D face synthesis

Abstract

This paper describes a system for automatic and real-time 3D photo-realistic face synthesis from a single frontal face image. This system employs a generic 3D head model approach for 3D face synthesis which can generate the 3D mapped face in real-time. The system first automatically detects face features from the input face image that corresponds to landmark points on the generic 3D head model. Thereafter, the generic head model is deformed to match the detected features. Finally, the texture from the face image is mapped onto the deformed 3D head model to create a photo-realistic 3D face. The system has the advantage of being totally automatic and runs in real-time. Experiments conducted show that good results can be obtained with no user intervention. Such a system is useful in many applications such as creation of avatar for virtual world by end-user with no need for manual and tedious process such as manual feature placements on the face image.