Papers › Look at Boundary: A Boundary-Aware Face Alignment Algorithm
Look at Boundary: A Boundary-Aware Face Alignment Algorithm
Wayne Wu, Chen Qian, Shuo Yang, Quan Wang, Yici Cai, Qiang Zhou
We present a novel boundary-aware face alignment algorithm by utilising boundary lines as the geometric structure of a human face to help facial landmark localisation. Unlike the conventional heatmap based method and regression based method, our approach derives face landmarks from boundary lines which remove the ambiguities in the landmark definition. Three questions are explored and answered by this work: 1. Why using boundary? 2. How to use boundary? 3. What is the relationship between boundary estimation and landmarks localisation? Our boundary- aware face alignment algorithm achieves 3.49% mean error on 300-W Fullset, which outperforms state-of-the-art methods by a large margin. Our method can also easily integrate information from other datasets. By utilising boundary information of 300-W dataset, our method achieves 3.92% mean error with 0.39% failure rate on COFW dataset, and 1.25% mean error on AFLW-Full dataset. Moreover, we propose a new dataset WFLW to unify training and testing across different factors, including poses, expressions, illuminations, makeups, occlusions, and blurriness. Dataset and model will be publicly available at https://wywu.github.io/projects/LAB/LAB.html
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Face Alignment | 300W | LAB | NME_inter-ocular (%, Challenge) | 5.19 | #29 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | LAB | NME_inter-ocular (%, Common) | 2.98 | #29 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | LAB | NME_inter-ocular (%, Full) | 3.49 | #29 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | LAB | NME_inter-pupil (%, Challenge) | 6.98 | #29 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | LAB | NME_inter-pupil (%, Common) | 3.42 | #29 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | LAB | NME_inter-pupil (%, Full) | 4.12 | #29 of 48 | Archive leaderboard | report |
| Face Alignment | AFLW-19 | LAB (w/ B) | NME_diag (%, Frontal) | 1.14 | #4 of 23 | Archive leaderboard | report |
| Face Alignment | AFLW-19 | LAB (w/ B) | NME_diag (%, Full) | 1.25 | #4 of 23 | Archive leaderboard | report |
| Face Alignment | AFLW-19 | LAB (w/o B) | NME_diag (%, Frontal) | 1.62 | #15 of 23 | Archive leaderboard | report |
| Face Alignment | AFLW-19 | LAB (w/o B) | NME_diag (%, Full) | 1.85 | #15 of 23 | Archive leaderboard | report |
| Face Alignment | COFW | LAB (w/ B) | NME (inter-ocular) | 3.92% | #18 of 28 | Archive leaderboard | report |
| Face Alignment | COFW | LAB | NME (inter-ocular) | 5.58% | #21 of 28 | Archive leaderboard | report |
| Face Alignment | WFLW | LAB | AUC@10 (inter-ocular) | 53.2 | #29 of 36 | Archive leaderboard | report |
| Face Alignment | WFLW | LAB | FR@10 (inter-ocular) | 7.56 | #29 of 36 | Archive leaderboard | report |
| Face Alignment | WFLW | LAB | NME (inter-ocular) | 5.27 | #29 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