Using stereo camera system to realize realistic video avatar in virtual environment

With the appearance of different kinds of virtual environment systems, the technology of realistic video avatar is becoming a hotspot of research. Our target is to create a realistic video avatar with less hardware investment and limited computation. In this paper, we introduce a method that combines a single stereo camera and 3D head model to engender a realistic video avatar. To engender the video avatar´s most important part - the face part - we use the 2D image and depth map, which is generated by the stereo camera. To engender the other parts of the 3D head model, we map the head´s texture to the 3D head model.