Papers › Efficient and Accurate Face Alignment by Global Regression and Cascaded Local Refinement
Efficient and Accurate Face Alignment by Global Regression and Cascaded Local Refinement
Jinzhan Su, Zhe Wang, Chunyuan Liao, Haibin Ling
Despite great advances witnessed on facial image alignment in recent years, high accuracy high speed face alignment algorithms still have rooms to improve especially for applications where computation resources are limited. Addressing this issue, we propose a new face landmark localization algorithm by combining global regression and local refinement. In particular, for a given image, our algorithm first estimates its global facial shape through a global regression network (GRegNet) and then using cascaded local refinement networks (LRefNet) to sequentially improve the alignment result. Compared with previous face alignment algorithms, our key innovation is the sharing of low level features in GRegNet with LRefNet. Such feature sharing not only significantly improves the algorithm efficiency, but also allows full exploration of rich locality-sensitive details carried with shallow network layers and consequently boosts the localization accuracy. The advantages of our algorithm is clearly validated in our thorough experiments on four popular face alignment benchmarks, 300-W, AFLW, COFW and WFLW. On all datasets, our algorithm produces state-of-the-art alignment accuracy, while enjoys the smallest computational complexity.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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 | GRegNet + LRefNet | NME_inter-ocular (%, Challenge) | 4.78 | #14 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | GRegNet + LRefNet | NME_inter-ocular (%, Common) | 2.71 | #14 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | GRegNet + LRefNet | NME_inter-ocular (%, Full) | 3.12 | #14 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | GRegNet + LRefNet | NME_inter-pupil (%, Challenge) | 6.89 | #14 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | GRegNet + LRefNet | NME_inter-pupil (%, Common) | 3.76 | #14 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | GRegNet + LRefNet | NME_inter-pupil (%, Full) | 4.37 | #14 of 48 | Archive leaderboard | report |
| Face Alignment | WFLW | GRegNet + LRefNet | AUC@10 (inter-ocular) | 58.4 | #25 of 36 | Archive leaderboard | report |
| Face Alignment | WFLW | GRegNet + LRefNet | FR@10 (inter-ocular) | 4.88 | #25 of 36 | Archive leaderboard | report |
| Face Alignment | WFLW | GRegNet + LRefNet | NME (inter-ocular) | 4.65 | #25 of 36 | 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.
Methods
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