Learning novel views to a single face image

A new technique is described for synthesizing images of faces from new viewpoints, when only a single 2D image from a known viewpoint is available. A novel 2D image of a face can be computed without knowledge about the 3D structure of the head. The technique draws on prior knowledge of faces based on example images of other faces seen in different poses and on a single generic 3D model of a human head. The example images are used to learn a pose-invariant shape and texture description of a new face. The 3D model is used to solve the correspondence problem between images showing faces in different poses. Examples of synthetic "rotations" over 24/spl deg/ based on a training set of 100 faces are shown.