Virtual face implant for visual character variations

One of the main goals in populating the virtual environments (VEs) with human body models is to increase the visual realism of the simulation. Population created with a template model cloning technique is perceived by the viewer as a synthetic crowd. To increase the degree of the visual realism, mainly the characters are generated with various body sizes and solid skin colors. In the case of avatars, a geometric model is customized according to the features of the real counterpart. In this paper we represent a simple and efficient method to improve the visual variance of the virtual characters by implanting a low resolution on any portrait face image. The effect of this model customization process is improved by adapting the whole body skin color with the average color tone calculated over the input face image.

[1]  Hong Yan,et al.  An Analytic-to-Holistic Approach for Face Recognition Based on a Single Frontal View , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[3]  K. P. Chow,et al.  Super-Resolution of Faces Using Texture Mapping on a Generic 3D Model , 2009, 2009 Fifth International Conference on Image and Graphics.

[4]  Scott Schaefer,et al.  Image deformation using moving least squares , 2006, ACM Trans. Graph..

[5]  K. P. Chow,et al.  Automatic 3D face texture mapping framework from single image , 2009, ICIMCS '09.

[6]  Hanspeter Pfister,et al.  Face transfer with multilinear models , 2005, SIGGRAPH 2005.

[7]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[8]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[10]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[11]  Seung-Yeob Baek,et al.  3D face model reconstruction from single 2D frontal image , 2009, VRCAI '09.

[12]  Simon Baker,et al.  2D vs. 3D Deformable Face Models: Representational Power, Construction, and Real-Time Fitting , 2007, International Journal of Computer Vision.