A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment
In this paper we present DCFE, a real-time facial landmark regression method based on a coarse-to-fine Ensemble of Regression Trees (ERT). We use a simple Convolutional Neural Network (CNN) to generate probability maps of landmarks location. These are further refined with the ERT regressor, which is initialized by fitting a 3D face model to the landmark maps. The coarse-to-fine structure of the ERT lets us address the combinatorial explosion of parts deformation. With the 3D model we also tackle other key problems such as robust regressor initialization, self occlusions, and simultaneous frontal and profile face analysis. In the experiments DCFE achieves the best reported result in AFLW, COFW, and 300W private and common public data sets.
PDF AbstractCode
300W
AFLW
COFW
Results from the Paper
Ranked #2 on
Face Alignment
on 300W Split 2
(FR@8 (inter-ocular) metric)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Face Alignment | 300W | DCFE | NME_inter-ocular (%, Full) | 3.24 | # 19 | |
| NME_inter-ocular (%, Common) | 2.76 | # 17 | ||||
| NME_inter-ocular (%, Challenge) | 5.22 | # 28 | ||||
| NME_inter-pupil (%, Full) | 4.55 | # 13 | ||||
| NME_inter-pupil (%, Common) | 3.83 | # 13 | ||||
| NME_inter-pupil (%, Challenge) | 7.54 | # 16 | ||||
| Facial Landmark Detection | 300W | DCFE (Inter-ocular Norm) | NME | 3.24 | # 5 | |
| Face Alignment | 300W Split 2 | DCFE | NME (inter-ocular) | 3.88 | # 3 | |
| AUC@8 (inter-ocular) | 52.42 | # 3 | ||||
| FR@8 (inter-ocular) | 1.83 | # 2 | ||||
| Facial Landmark Detection | AFLW-Full | DCFE (Box height Norm, 19 landmarks - no earlobs) | Mean NME | 2.17 | # 4 | |
| Face Alignment | COFW | DCFE | NME (inter-pupil) | 5.27% | # 6 | |
| Face Alignment | IBUG | DCFE (inter pupils normalization) | Mean Error Rate | 7.54% | # 2 |
