General Human Traits Oriented Generic Elastic Model for 3D Face Reconstruction

We propose a Simplified Generic Elastic Model (S-GEM) which intends to construct a 3D face from a given 2D face image by making use of a set of general human traits viz., Gender, Ethnicity and Age (GEA). We hypothesise that the variations inherent on the depth information for individuals are significantly mitigated by narrowing down the target information via a selection of specific GEA traits. In this paper, we propose a 3D reconstruction method to retain the robustness of the PCA-based models and in the meantime to provide control over the depth values of 2D facial feature points. We formulate the reconstruction of the 3D face model of a given 2D face image as a posterior estimation of the PC coefficients Φ given the observations of the 2D facial feature points x f . The depth value Z of the 2D feature points is expressed as the hidden information. The posterior probability is represented as the marginal distribution of P(Φ|x f ) integrated over Z as shown below: