Minimum variance estimation of 3D face shape from multi-view

Zhenqiu Zhang, Yuxiao Hu, Tianli Yu, Thomas Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A minimum variance estimation framework for 3D face reconstruction from multiple views and a new 3D surface reconstruction algorithm based on deformable subdivision mesh is proposed in this paper. First, an efficient 2D-to-3D integrated face reconstruction approach is introduced to reconstruct a personalized 3D face model from a single frontal face image with minimum variance estimation; Then, a new deformable mesh based surface reconstruction algorithm is applied to the images from different views to get more observation of the 3D face, especially the depth information, which could not be obtained from a single image directly; Based on the result of the 3D surface reconstruction, we use the minimum variance estimation again to refine the estimation of the 3D face. We combine the texture from different views, and the result looks photorealistic.

Original languageEnglish (US)
Title of host publicationFGR 2006
Subtitle of host publicationProceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Pages547-552
Number of pages6
DOIs
StatePublished - 2006
Externally publishedYes
EventFGR 2006: 7th International Conference on Automatic Face and Gesture Recognition - Southampton, United Kingdom
Duration: Apr 10 2006Apr 12 2006

Publication series

NameFGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Volume2006

Other

OtherFGR 2006: 7th International Conference on Automatic Face and Gesture Recognition
Country/TerritoryUnited Kingdom
CitySouthampton
Period4/10/064/12/06

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint

Dive into the research topics of 'Minimum variance estimation of 3D face shape from multi-view'. Together they form a unique fingerprint.

Cite this