A morphable model for the synthesis of 3D faces
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Face Model Adaptation using Robust Matching and Active Appearance Models
WACV '02 Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision
Regularized 3D Morphable Models
HLK '03 Proceedings of the First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis
A Statistical Method for Robust 3D Surface Reconstruction from Sparse Data
3DPVT '04 Proceedings of the 3D Data Processing, Visualization, and Transmission, 2nd International Symposium
Accurate 3D Tracking of Rigid Objects with Occlusion Using Active Appearance Models
WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Real-time combined 2D+3D active appearance models
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Hi-index | 0.00 |
Estimating the structure of the human face is a long studied and difficult task. In this paper we present a new method for estimating facial structure from only a minimal number of salient feature points across a video sequence. The presented method uses both an Extended Kalman Filter (EKF) and a Kalman Filter (KF) to regress 3D Morphable Model (3DMM) shape parameters and solve 3D pose using a simplified camera model. A linear method for initializing the recursive pose filter is provided. The convergence properties of the method are then evaluated using synthetic data. Finally, using the same synthetic data the method is demonstrated for both single image shape recovery and shape recovery across a sequence.