A novel deformation framework for face modeling from a few control points

Authors:
Xun Gong;Guoyin Wang
Affiliations:
Institute of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, P.R. China and School of Information Science and Technology, Southwest Jiaotong Unive ...;Institute of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, P.R. China and School of Information Science and Technology, Southwest Jiaotong Unive ...
Venue:
RSKT'08 Proceedings of the 3rd international conference on Rough sets and knowledge technology
Year:
2008

Citing 6
Cited 2

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
Computer generated animation of faces

ACM '72 Proceedings of the ACM annual conference - Volume 1
Combining PCA and LFA for Surface Reconstruction from a Sparse Set of Control Points

FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
A dynamic component deforming model for face shape reconstruction

ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part I
Accurate face models from uncalibrated and Ill-Lit video sequences

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition

Probabilistic Modeling and Visualization of the Flexibility in Morphable Models

Proceedings of the 13th IMA International Conference on Mathematics of Surfaces XIII
Perspectives on Cognitive Informatics and Cognitive Computing

International Journal of Cognitive Informatics and Natural Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel method to reconstruct realistic 3D faces from a set of control points: (i) a local deformation approach is proposed, which could effectively preserve the information when only a few features are known; (ii) a Ternary Deformation Framework (TDF), combining the strengths of both local modification and global calculation, is developed to accurately recover the face shape. Simulation results show that TDF outperforms the conventional methods with respect to the modeling precision and could generate realistic face models.