Sciweavers

Share
ICPR
2010
IEEE

3D Face Reconstruction Using a Single or Multiple Views

9 years 1 days ago
3D Face Reconstruction Using a Single or Multiple Views
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.
Jongmoo Choi, Gérard G. Medioni, Yuping Lin
Added 07 Dec 2010
Updated 07 Dec 2010
Type Conference
Year 2010
Where ICPR
Authors Jongmoo Choi, Gérard G. Medioni, Yuping Lin, Luciano Silva, Olga Regina Pereira Bellon, Mauricio Pamplona, Timothy C. Faltemier
Comments (0)
books