Model-based stereo with occlusions
AMFG'07 Proceedings of the 3rd international conference on Analysis and modeling of faces and gestures
Deformable Model Fitting by Regularized Landmark Mean-Shift
International Journal of Computer Vision
3D morphable model parameter estimation
AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Generic active appearance models revisited
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
A review of motion analysis methods for human Nonverbal Communication Computing
Image and Vision Computing
Robust Bayesian fitting of 3D morphable model
Proceedings of the 10th European Conference on Visual Media Production
| Hi-index | 0.00 |
Three-dimensional morphable models of object classes are a powerfultool in modeling, animation and recognition. We introduce here thenew concept of regularized 3D morphable models, along with aniterative learning algorithm, by adding in the statistical model anoise/regularization term which is estimated from the examples set.With regularized 3D morphable models we are able to handle missinginformation, as it often occurs with data obtained by 3Dacquisition systems; additionally, the new models are less complexthan, but as powerful as the non-regularized ones. We present theresults obtained for a set of 3D face models and a comparison withthe ones obtained by a traditional morphable model on the same dataset.