Automatic 3d face model reconstruction using one image

Authors:
Chen Lu;Yang Jie
Affiliations:
Institute of Image Processing and Pattern Recognition, Shanghai Jiao tong University, Shanghai, China;Institute of Image Processing and Pattern Recognition, Shanghai Jiao tong University, Shanghai, China
Venue:
IWICPAS'06 Proceedings of the 2006 Advances in Machine Vision, Image Processing, and Pattern Analysis international conference on Intelligent Computing in Pattern Analysis/Synthesis
Year:
2006

Citing 8
Cited 0

Principal Warps: Thin-Plate Splines and the Decomposition of Deformations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Active shape models—their training and application

Computer Vision and Image Understanding
Active Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition Based on Fitting a 3D Morphable Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Imaged-Based 3D Face Modeling

CGIV '04 Proceedings of the International Conference on Computer Graphics, Imaging and Visualization
Realistic Face Modeling With Robust Correspondences

IV '04 Proceedings of the Information Visualisation, Eighth International Conference
3D face modeling using two orthogonal views and a generic face model

ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 3 (ICME '03) - Volume 03
Efficient 3D reconstruction for face recognition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we reconstruct the corresponding 3D face model using only one 2D image. 3D feature points are obtained by optimally approximating 2D feature points set with defined similarity. Then, a shape model is reconstructed by the warp function algorithm. Finally, a realistic face model is created through texture mapping with registration method such as affine transform. Results show that the models we reconstruct are comparatively realistic, and they can be used for face recognition or computer animation. The computation speed is also satisfying.