Papers › A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment
A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment
Roberto Valle, Jose M. Buenaposada, Antonio Valdes, Luis Baumela
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.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Face Alignment | 300W | DCFE | NME_inter-ocular (%, Challenge) | 5.22 | #19 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | DCFE | NME_inter-ocular (%, Common) | 2.76 | #19 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | DCFE | NME_inter-ocular (%, Full) | 3.24 | #19 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | DCFE | NME_inter-pupil (%, Challenge) | 7.54 | #19 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | DCFE | NME_inter-pupil (%, Common) | 3.83 | #19 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | DCFE | NME_inter-pupil (%, Full) | 4.55 | #19 of 48 | Archive leaderboard | report |
| Face Alignment | 300W Split 2 | DCFE | AUC@8 (inter-ocular) | 52.42 | #6 of 7 | Archive leaderboard | report |
| Face Alignment | 300W Split 2 | DCFE | FR@8 (inter-ocular) | 1.83 | #6 of 7 | Archive leaderboard | report |
| Face Alignment | 300W Split 2 | DCFE | NME (inter-ocular) | 3.88 | #6 of 7 | Archive leaderboard | report |
| Face Alignment | COFW | DCFE | NME (inter-pupil) | 5.27% | #26 of 28 | Archive leaderboard | report |
| Face Alignment | IBUG | DCFE (inter pupils normalization) | Mean Error Rate | 7.54% | #2 of 2 | Archive leaderboard | report |
| Facial Landmark Detection | 300W | DCFE (Inter-ocular Norm) | NME | 3.24 | #6 of 15 | Archive leaderboard | report |
| Facial Landmark Detection | AFLW-Full | DCFE (Box height Norm, 19 landmarks - no earlobs) | Mean NME | 2.17 | #4 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections