Interactive composition of 3D faces for virtual characters

Authors:
Haeyoung Lee;Sungyeol Lee
Affiliations:
Hongik University, Dept. of Computer Engineering, Mapogu, Seoul, Korea;Hongik University, Dept. of Computer Engineering, Mapogu, Seoul, Korea
Venue:
Edutainment'07 Proceedings of the 2nd international conference on Technologies for e-learning and digital entertainment
Year:
2007

Citing 12
Cited 0

A muscle model for animation three-dimensional facial expression

SIGGRAPH '87 Proceedings of the 14th annual conference on Computer graphics and interactive techniques
Algorithms for solid noise synthesis

SIGGRAPH '89 Proceedings of the 16th annual conference on Computer graphics and interactive techniques
Numerical recipes in C (2nd ed.): the art of scientific computing

Numerical recipes in C (2nd ed.): the art of scientific computing
Realistic modeling for facial animation

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Computer facial animation

Computer facial animation
Synthesizing realistic facial expressions from photographs

Proceedings of the 25th annual conference on Computer graphics and interactive techniques
A morphable model for the synthesis of 3D faces

Proceedings of the 26th annual conference on Computer graphics and interactive techniques
Interactive mesh fusion based on local 3D metamorphosis

Proceedings of the 1999 conference on Graphics interface '99
Shape by example

I3D '01 Proceedings of the 2001 symposium on Interactive 3D graphics
Modeling by example

ACM SIGGRAPH 2004 Papers
Geodesics-Based One-to-One Parameterization of 3D Triangle Meshes

IEEE MultiMedia
Automatic 3D Face Modeling from Video

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

As many 3D on-line games appear, there is an increased need for simple and efficient techniques to create many new faces. This paper presents a new algorithm to composite 3D faces for game characters. No remeshing or segmentation of 3D models is required in our method. Our algorithm is composed of four simple steps: building a one-to-one geometric correspondence between models, local resampling, computing relative geometry, and blending geometry. Our new algorithm can provide various composite operations such as replacement, interpolation, or randomization by assigning different weights for geometry blending. The space and time complexity of our algorithm is linear to the combined number of vertices of input meshes which means it is efficient enough for interactive operation. Our new method is expected to easily and quickly give a unique appearance to 3D game characters or anonymous crowds.