Adaptive Multi-Resolution Fitting and its Application to Realistic Head Modeling

Authors:
Affiliations:
Venue:
GMP '04 Proceedings of the Geometric Modeling and Processing 2004
Year:
2004

Citing 0
Cited 3

Automatic 3D face recognition combining global geometric features with local shape variation information

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
3D face recognition based on g-h shape variation

SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
An automatic method of building 3d morphable face model

IWBRS'05 Proceedings of the 2005 international conference on Advances in Biometric Person Authentication

Quantified Score

Hi-index	0.00

Visualization

Abstract

The general approach for object modeling is to constructthe surface from the high-quality range points obtainedfrom laser scanners. In this paper, we face the noise pointcloud obtained from image sequences by a commoncamera and develop a novel algorithm of AdaptiveMulti-Resolution Fitting (AMRF) for object modeling. Thisalgorithm combines the adaptive subdivision scheme withmulti-resolution fitting so that the control model issubdivided locally and adaptively according to the localcomplexity of the point cloud and approximates the 3Ddata level by level. The proposed method can conquer theholes and outliers efficiently and create full compatibilitybetween the complexity of the mesh model and therepresentation of the local details. We apply the proposedmethod to the complete head modeling with the real data,and the results seem very promising.