Model-assisted face reconstruction based on binocular stereo

Xi Sun; Ying Zheng; Zengfu Wang

doi:10.1117/12.863269

Translator Disclaimer

4 August 2010 Model-assisted face reconstruction based on binocular stereo

Xi Sun, Ying Zheng, Zengfu Wang

Author Affiliations +

Proceedings Volume 7744, Visual Communications and Image Processing 2010; 77442Y (2010) https://doi.org/10.1117/12.863269
Event: Visual Communications and Image Processing 2010, 2010, Huangshan, China

Abstract

In this paper we propose a model-assisted binocular stereo algorithm for 3D face reconstruction. First, stereo correspondence is reliably performed between input stereo images by employing a 3D reference face model as a medium. Then, a high-quality dataset of point cloud is generated by triangulation from the stereo correspondence. Finally, an accurate and feature-preserving 3D face surface is reconstructed from the point cloud dataset by a denoising operation of bilateral filtering and surface meshing. We have compared the reconstructed faces with ground truth 3D data. The experimental results show that the proposed algorithm is effective with the average error of 2.6mm.

Citation Download Citation

Xi Sun, Ying Zheng, and Zengfu Wang "Model-assisted face reconstruction based on binocular stereo", Proc. SPIE 7744, Visual Communications and Image Processing 2010, 77442Y (4 August 2010); https://doi.org/10.1117/12.863269

ACCESS THE FULL ARTICLE