Fitting a 3D Morphable Model to Edges: A Comparison Between Hard and Soft Correspondences - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

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

Résumé

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.
Fichier principal
Vignette du fichier
bas_etal_2016.pdf (9.78 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01271343 , version 1 (09-02-2016)
hal-01271343 , version 2 (07-10-2016)

Identifiants

Citer

Anil Bas, William A. P. Smith, Timo Bolkart, Stefanie Wuhrer. Fitting a 3D Morphable Model to Edges: A Comparison Between Hard and Soft Correspondences. Asian Conference on Computer Vision Workshop on Facial Informatics, Nov 2016, Taipei, Taiwan. pp.377-391, ⟨10.1007/978-3-319-54427-4_28⟩. ⟨hal-01271343v2⟩
578 Consultations
2454 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More