3D Face Reconstruction Using a Single or Multiple Views

Authors:
Jongmoo Choi;Gerard Medioni;Yuping Lin;Luciano Silva;Olga Regina;Mauricio Pamplona;Timothy C. Faltemier
Affiliations:
-;-;-;-;-;-;-
Venue:
ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Year:
2010

Citing 0
Cited 2

Fast-automatic 3D face generation using a single video camera

ACM SIGGRAPH 2012 Posters
Automatic system for virtual human reconstruction with 3D mesh multi-texturing and facial enhancement

Image Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a 3D face reconstruction system that takes as input either one single view or several different views. Given a facial image, we first classify the facial pose into one of five predefined poses, then detect two anchor points that are then used to detect a set of predefined facial landmarks. Based on these initial steps, for a single view we apply a warping process using a generic 3D face model to build a 3D face. For multiple views, we apply sparse bundle adjustment to reconstruct 3D landmarks which are used to deform the generic 3D face model. Experimental results on the Color FERET and CMU multi-PIE databases confirm our framework is effective in creating realistic 3D face models that can be used in many computer vision applications, such as 3D face recognition at a distance.