Face modeling and wrinkle simulation using convolution surface

Authors:
Qing He;Minglei Tong;Yuncai Liu
Affiliations:
Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai, China;Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai, China;Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai, China
Venue:
AMDO'06 Proceedings of the 4th international conference on Articulated Motion and Deformable Objects
Year:
2006

Citing 7
Cited 0

Convolution surfaces

Proceedings of the 18th annual conference on Computer graphics and interactive techniques
Convolution surfaces for line skeletons with polynomial weight distributions

Journal of Graphics Tools
A Simple Method for Modeling Wrinkles on Human Skin

PG '02 Proceedings of the 10th Pacific Conference on Computer Graphics and Applications
Skeletal Methods of Shape Manipulation

SMI '99 Proceedings of the International Conference on Shape Modeling and Applications
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
Realistic and efficient wrinkle simulation using an anatomy-based face model with adaptive refinement

CGI '05 Proceedings of the Computer Graphics International 2005
Recover human pose from monocular image under weak perspective projection

ICCV'05 Proceedings of the 2005 international conference on Computer Vision in Human-Computer Interaction

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new method to simulate wrinkles on individual face model, applying convolution surface to face modeling. A generic face mesh is deformed and the texture image is computed using image-based modeling technique. The deformed mesh is then convolved with a kernel function to generate a convolution surface, and wrinkles are generated by modulating the surface with a designed profile function. The pre-computed texture is mapped onto the convolution surface to enhance the realism. Experimental results show that our method can generate wrinkles with different patterns by regulating some parameters of the profile function