Dense 3D Face Correspondence
We present an algorithm that automatically establishes dense correspondences between a large number of 3D faces. Starting from automatically detected sparse correspondences on the convex hull of 3D faces, the algorithm triangulates existing correspondences and expands them iteratively along the triangle edges. New correspondences are established by matching keypoints on the geodesic patches along the triangle edges and the process is repeated. After exhausting keypoint matches, further correspondences are established by evolving level set geodesic curves from the centroids of large triangles. A deformable model (K3DM) is constructed from the dense corresponded faces and an algorithm is proposed for morphing the K3DM to fit unseen faces. This algorithm iterates between rigid alignment of an unseen face followed by regularized morphing of the deformable model. We have extensively evaluated the proposed algorithms on synthetic data and real 3D faces from the FRGCv2 and BU3DFE databases using quantitative and qualitative benchmarks. Our algorithm achieved dense correspondences with a mean localization error of 1.28mm on synthetic faces and detected 18 anthropometric landmarks on unseen real faces from the FRGCv2 database with 3mm precision. Furthermore, our deformable model fitting algorithm achieved 99.8 accuracy on the FRGCv2 database.
READ FULL TEXT