ABSTRACT

In this paper, we describe image-based modeling tech­ niques that make possible the creation of photo-realistic computer models of real human faces. The image-based model is built using example views of the face, bypassing the need for any three-dimensional computer graphics models. A learning network is trained to associate each of the example images with a set of pose and expres­ sion parameters. For a novel set of parameters, the network synthesizes a novel, intermediate view using a view morphing approach. This image-based synthesis paradigm can adequately model both rigid and non-rigid facial movements.