Mesh resampling alignment for 3D face morphable model

Based on resampling method, we present a morphable model for 3D face synthesis. The morphable model can reconstruct 3D face automatically from facial image by the combination of aligning prototypic 3D faces. But the point-to-point alignment of 3D dense faces is a challengeable problem. The optical flow algorithm is used to compute the alignment by cylinder projective facial images. But this algorithm is a approximative and unstable method. We propose a mesh resampling method to do the alignment. Based on the resampling alignment a 3D face morpable model is constructed. And from the temporary data of mesh resampling a multi-resolution model is constructed to accelerate the model matching and improve its converging stability. The experimental results show, the resampling alignment is a contributive method for the morphable model in 3D face synthesis.