Robust and accurate shape model fitting using random forest regression voting
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
3D shape regression for real-time facial animation
ACM Transactions on Graphics (TOG) - SIGGRAPH 2013 Conference Proceedings
Sparsity sharing embedding for face verification
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Face parts localization using structured-output regression forests
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Generic active appearance models revisited
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Image and Vision Computing
Efficient mesh-based face beautifier on mobile devices
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Facial landmark localization based on hierarchical pose regression with cascaded random ferns
Proceedings of the 21st ACM international conference on Multimedia
A facial tracking and transfer method with a key point refinement
ACM SIGGRAPH 2013 Posters
Eye pupil localization with an ensemble of randomized trees
Pattern Recognition
| Hi-index | 0.00 |
We present a very efficient, highly accurate, “Explicit Shape Regression” approach for face alignment. Unlike previous regression-based approaches, we directly learn a vectorial regression function to infer the whole facial shape (a set of facial landmarks) from the image and explicitly minimize the alignment errors over the training data. The inherent shape constraint is naturally encoded into the regressor in a cascaded learning framework and applied from coarse to fine during the test, without using a fixed parametric shape model as in most previous methods. To make the regression more effective and efficient, we design a two-level boosted regression, shape-indexed features and a correlation-based feature selection method. This combination enables us to learn accurate models from large training data in a short time (20 minutes for 2,000 training images), and run regression extremely fast in test (15 ms for a 87 landmarks shape). Experiments on challenging data show that our approach significantly outperforms the state-of-the-art in terms of both accuracy and efficiency.