Rendering or normalization? An analysis of the 3D-aided pose-invariant face recognition

In spite of recent progress achieved in near-frontal face recognition, the problem of pose variations prevalent in 2D facial images captured in the wild still remains a challenging and unsolved issue. Among existing approaches of pose-invariant face recognition, 3D-aided methods have been demonstrated effective and promising. In this paper, we present an extensive evaluation of two widely adopted frameworks of 3D-aided face recognition in order to compare the state-of-the-art, identify remaining issues, and offer suggestions for future research. Specifically, we compare the pose normalization and the pose synthesis (rendering) based methods in an empirical manner. The database (UHDB31) that we use covers 21 well-controlled pose variations, half of which show a combination of yaw and pitch. Through the experiments, we present the advantages and disadvantages of these two methods to provide solid data for future research in 3D-aided pose-invariant face recognition.