3D Face Template Registration Using Normal Maps

This paper presents a semi-automatic method to fit a template mesh to high-resolution normal data, which is generated using spherical gradient illuminations in a light stage. Template fitting is an important step to build a 3D morph able face model, which can be employed for image-Based facial performance capturing. In contrast to existing 3D reconstruction approaches, we omit the structured light scanning step to obtain low-frequency 3D information and rely solely on normal data from multiple views. This reduces the acquisition time by over 50 percent. In our experiments the proposed algorithm is successfully applied to real faces of several subjects. Experiments with synthetic data show that the fitted face template can closely resemble the ground truth geometry.