Papers › AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses

AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses

7 Jul 2020arXiv:2007.03221archive 2025-07-28

Zixuan Xu, Banghuai Li, Miao Geng, Ye Yuan

Facial landmark localization aims to detect the predefined points of human faces, and the topic has been rapidly improved with the recent development of neural network based methods. However, it remains a challenging task when dealing with faces in unconstrained scenarios, especially with large pose variations. In this paper, we target the problem of facial landmark localization across large poses and address this task based on a split-and-aggregate strategy. To split the search space, we propose a set of anchor templates as references for regression, which well addresses the large variations of face poses. Based on the prediction of each anchor template, we propose to aggregate the results, which can reduce the landmark uncertainty due to the large poses. Overall, our proposed approach, named AnchorFace, obtains state-of-the-art results with extremely efficient inference speed on four challenging benchmarks, i.e. AFLW, 300W, Menpo, and WFLW dataset. Code will be available at https://github.com/nothingelse92/AnchorFace.

PaperPDFCode

In Syntology View this paper on Syntology: its page in Syntology's graph, with its repositories and citations.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

nothingelse92/AnchorFace officialmentioned in paper report

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

Face AlignmentFacial Landmark Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Alignment 300W AnchorFace NME_inter-ocular (%, Challenge) 6.19 #31 of 48 Archive leaderboard report
Face Alignment 300W AnchorFace NME_inter-ocular (%, Common) 3.12 #31 of 48 Archive leaderboard report
Face Alignment 300W AnchorFace NME_inter-ocular (%, Full) 3.72 #31 of 48 Archive leaderboard report
Face Alignment AFLW-19 AnchorFace NME_diag (%, Frontal) 1.38 #12 of 23 Archive leaderboard report
Face Alignment AFLW-19 AnchorFace NME_diag (%, Full) 1.56 #12 of 23 Archive leaderboard report
Face Alignment AFLW-Full AnchorFace Mean NME 1.56 #2 of 2 Archive leaderboard report
Face Alignment WFLW AnchorFace AUC@10 (inter-ocular) 57.69 #15 of 36 Archive leaderboard report
Face Alignment WFLW AnchorFace FR@10 (inter-ocular) 2.96 #15 of 36 Archive leaderboard report
Face Alignment WFLW AnchorFace NME (inter-ocular) 4.32 #15 of 36 Archive leaderboard report
Face Alignment WFW (Extra Data) AnchoFace AUC@10 (inter-ocular) 57.69 #7 of 11 Archive leaderboard report
Face Alignment WFW (Extra Data) AnchoFace FR@10 (inter-ocular) 2.96 #7 of 11 Archive leaderboard report
Face Alignment WFW (Extra Data) AnchoFace NME (inter-ocular) 4.32 #7 of 11 Archive leaderboard report
Facial Landmark Detection 300W AnchorFace NME 3.12 #4 of 15 Archive leaderboard report
Facial Landmark Detection 300W (Full) AnchorFace Mean NME 3.72 #2 of 2 Archive leaderboard report
Facial Landmark Detection AFLW-Front AnchorFace Mean NME 1.38 #2 of 3 Archive leaderboard report
Facial Landmark Detection AFLW-Full AnchorFace Mean NME 1.56 #2 of 5 Archive leaderboard report
Facial Landmark Detection AFLW-Full AnchorFace Mean NME 1.56 #2 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.

Methods

SPEED

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