Papers › PFLD: A Practical Facial Landmark Detector

PFLD: A Practical Facial Landmark Detector

28 Feb 2019arXiv:1902.10859archive 2025-07-28

Xiaojie Guo, Siyuan Li, Jinke Yu, Jiawan Zhang, Jiayi Ma, Lin Ma, Wei Liu, Haibin Ling

Being accurate, efficient, and compact is essential to a facial landmark detector for practical use. To simultaneously consider the three concerns, this paper investigates a neat model with promising detection accuracy under wild environments e.g., unconstrained pose, expression, lighting, and occlusion conditions) and super real-time speed on a mobile device. More concretely, we customize an end-to-end single stage network associated with acceleration techniques. During the training phase, for each sample, rotation information is estimated for geometrically regularizing landmark localization, which is then NOT involved in the testing phase. A novel loss is designed to, besides considering the geometrical regularization, mitigate the issue of data imbalance by adjusting weights of samples to different states, such as large pose, extreme lighting, and occlusion, in the training set. Extensive experiments are conducted to demonstrate the efficacy of our design and reveal its superior performance over state-of-the-art alternatives on widely-adopted challenging benchmarks, i.e., 300W (including iBUG, LFPW, AFW, HELEN, and XM2VTS) and AFLW. Our model can be merely 2.1Mb of size and reach over 140 fps per face on a mobile phone (Qualcomm ARM 845 processor) with high precision, making it attractive for large-scale or real-time applications. We have made our practical system based on PFLD 0.25X model publicly available at http://sites.google.com/view/xjguo/fld for encouraging comparisons and improvements from the community.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

18 repositories listed; official and paper-mentioned ones first.

AmrElsersy/PFLD-Pytorch-Landmarks mentioned on GitHubpytorchSyntology: not harvested report
Ontheway361/pfld-pytorch mentioned on GitHubpytorchSyntology: not harvested report
RomanticWithoutStatus/PFLD-TensorFlow2caffe mentioned on GitHubtfSyntology: not harvested report
SpikeKing/Gaze4Landmarks mentioned on GitHubpytorchSyntology: not harvested report
ainrichman/Peppa-Facial-Landmark-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
epoc88/PFLD_68pts_Pytorch_2020 mentioned on GitHubmxnetSyntology: not harvested report
github-luffy/PFLD-68points-tensorflow mentioned on GitHubmxnetSyntology: not harvested report
github-luffy/PFLD_68points_Pytorch mentioned on GitHubmxnetSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
guoqiangqi/PFLD mentioned on GitHubtfSyntology: not harvested report
nilseuropa/pfdl_ncnn mentioned on GitHubpytorchSyntology: not harvested report
nilseuropa/pfld_ncnn mentioned on GitHubpytorchSyntology: not harvested report
olegpolivin/antisleep mentioned on GitHubpytorchSyntology: not harvested report
polarisZhao/PFLD-pytorch mentioned on GitHubpytorchSyntology: not harvested report
samuelyu2002/PFLD mentioned on GitHubpytorchSyntology: not harvested report
starhiking/ATF mentioned on GitHubpytorchSyntology: not harvested report
SongJieLiu/pfld mindsporeSyntology: not harvested report
xiuyu0000/papers_with_examples mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Lite-HRNet: A Lightweight High-Resolution Network (arXiv:2104.06403; that paper's own run record: 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
yangyucheng000/pfld mindsporeSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

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

No leaderboard rows for this paper in the archive.

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