A Robust Method for Facial Shape and Texture Reconstruction Overcoming the Influence of Shadow and Highlight

Abstract

This paper presents a robust method for facial shape and texture reconstruction based-on the model of polyhedron and the technology of photometric stereo. Using the continuity restrictions and error-reduced operator, the presented method can overcome the influence of shadow and highlight. First, we reconstruct the 2.5D shape and texture of human face by solving a linear equations system established by the corresponding relationships between faces of polyhedron and pixels of human facial images under three independent illuminations. Then, we synthesize three virtual photometric stereo images from reconstructed shape and texture using computer graphics. The local shadow analysis and specular reflection are used to make the synthesized images approach to the real images. We reconstruct facial shape and texture again from synthesized virtual photometric stereo images. Finally, these two reconstruction results are combined to reduce the reconstruction error and produce a superior result. Experimental results on YaleB database show that this method can reconstruct the 2.5D shape and texture of human face rapidly overcoming the influence of shadow and highlight.