Abstract : In this paper we explore the problem of fitting a 3D morphable model to single face images using only sparse geometric features (edges and landmark points). Previous approaches to this problem are based on nonlinear optimisation of an edge-derived cost that can be viewed as forming soft correspondences between model and image edges. We propose a novel approach, that explicitly computes hard correspondences. The resulting objective function is non-convex but we show that a good initialisation can be obtained efficiently using alternating linear least squares in a manner similar to the iterated closest point algorithm. We present experimental results on both synthetic and real images and show that our approach outperforms methods that use soft correspondence and other recent methods that rely solely on geometric features.
https://hal.inria.fr/hal-01271343
Contributeur : Stefanie Wuhrer <>
Soumis le : vendredi 7 octobre 2016 - 09:46:32
Dernière modification le : vendredi 28 octobre 2016 - 14:56:28
Document(s) archivé(s) le : dimanche 8 janvier 2017 - 12:25:52
Anil Bas, William A. P. Smith, Timo Bolkart, Stefanie Wuhrer. Fitting a 3D Morphable Model to Edges: A Comparison Between Hard and Soft Correspondences. ACCV Workshop on Facial Informatics, Nov 2016, Taipei, Taiwan. <hal-01271343v2>
