Fitting a 3D Morphable Model to Edges: A Comparison Between Hard and Soft Correspondences


Bas A. , Smith W. A. P. , Bolkart T., Wuhrer S.

13th Asian Conference on Computer Vision (ACCV), Taipei, Tayvan, 20 - 24 Kasım 2016, cilt.10117, ss.377-391 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 10117
  • Doi Numarası: 10.1007/978-3-319-54427-4_28
  • Basıldığı Şehir: Taipei
  • Basıldığı Ülke: Tayvan
  • Sayfa Sayıları: ss.377-391

Özet

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.