Superfaces: A Super-Resolution Model for 3D Faces

Abstract

Face recognition based on the analysis of 3D scans has been an active research subject over the last few years. However, the impact of the resolution of 3D scans on the recognition process has not been addressed explicitly yet being of primal importance after the introduction of a new generation of low cost 4D scanning devices. These devices are capable of combined depth/rgb acquisition over time with a low resolution compared to the 3D scanners typically used in 3D face recognition benchmarks. In this paper, we define a super-resolution model for 3D faces by which a sequence of low-resolution 3D scans can be processed to extract a higher resolution 3D face model, namely the superface model. The proposed solution relies on the Scaled ICP procedure to align the low-resolution 3D models with each other and estimate the value of the high-resolution 3D model based on the statistics of values of the low-resolution scans in corresponding points. The approach is validated on a data set that includes, for each subject, one sequence of low-resolution 3D face scans and one ground-truth high-resolution 3D face model acquired through a high-resolution 3D scanner. In this way, results of the super-resolution process are evaluated qualitatively and quantitatively by measuring the error between the superface and the ground-truth.