30 January 2012 Refined facial disparity maps for automatic creation of 3D avatars
Author Affiliations +
We propose a new method to automatically refine a facial disparity map obtained with standard cameras and under conventional illumination conditions by using a smart combination of traditional computer vision and 3D graphics techniques. Our system inputs two stereo images acquired with standard (calibrated) cameras and uses dense disparity estimation strategies to obtain a coarse initial disparity map, and SIFT to detect and match several feature points in the subject's face. We then use these points as anchors to modify the disparity in the facial area by building a Delaunay triangulation of their convex hull and interpolating their disparity values inside each triangle. We thus obtain a refined disparity map providing a much more accurate representation of the the subject's facial features. This refined facial disparity map may be easily transformed, through the camera calibration parameters, into a depth map to be used, also automatically, to improve the facial mesh of a 3D avatar to match the subject's real human features.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Rafael Pagés, Rafael Pagés, Francisco Morán, Francisco Morán, Luis Salgado, Luis Salgado, Daniel Berjón, Daniel Berjón, } "Refined facial disparity maps for automatic creation of 3D avatars", Proc. SPIE 8290, Three-Dimensional Image Processing (3DIP) and Applications II, 82900J (30 January 2012); doi: 10.1117/12.908259; https://doi.org/10.1117/12.908259


Camera self-calibration method based on two vanishing points
Proceedings of SPIE (October 07 2015)
3D imaging: how to achieve highest accuracy
Proceedings of SPIE (June 21 2011)
Vision system for telerobotics operation
Proceedings of SPIE (September 30 1992)
Level-set approach for stereo
Proceedings of SPIE (February 18 1997)

Back to Top