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

Anil Bas 1 William Smith 1 Timo Bolkart 2 Stefanie Wuhrer 3
1 Department of Computer Science
2 M2CI - Cluster of Excellence "Multimodal Computing and Interaction" [Saarbrücken]
3 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
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.
Keywords : face shape estimation 3D morphable model edge detection iterated closest point
Document type :
Conference papers
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download
https://hal.inria.fr/hal-01271343
Contributor : Stefanie Wuhrer <>
Submitted on : Friday, October 7, 2016 - 9:46:32 AM
Last modification on : Tuesday, October 1, 2019 - 3:50:11 PM
Long-term archiving on: Sunday, January 8, 2017 - 12:25:52 PM

File

bas_etal_2016.pdf
Files produced by the author(s)

Identifiers

Collections

CNRS | INRIA | LJK | UGA | LJK_GI | LJK_GI_MORPHEO

Citation

Anil Bas, William 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⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

611

Files downloads

3107

 

 

Contact

archive-ouverte@inria.fr