{"url":"/sota/face-alignment-on-cofw","task":{"name":"Face Alignment","url":"/task/face-alignment","note":null},"dataset":{"name":"COFW","url":"/dataset/cofw"},"category":"Computer Vision","categories":["Computer Vision","Miscellaneous","Music"],"category_note":null,"description":"Face alignment is the task of identifying the geometric structure of faces in digital images, and attempting to obtain a canonical alignment of the face based on translation, scale, and rotation.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [3DDFA_V2](https://github.com/cleardusk/3DDFA_V2) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["NME (inter-ocular)","Recall at 80% precision (Landmarks Visibility)","NME (inter-pupil)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"NME (inter-ocular)":null,"Recall at 80% precision (Landmarks Visibility)":"higher","NME (inter-pupil)":null}},"counts":{"rows":28,"rows_with_code":20,"rows_with_paper_page":28,"rows_dated":28,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"FiFA","metrics":{"NME (inter-ocular)":"2.96"},"uses_additional_data":false,"paper_date":"2024-02-23","paper":"/paper/fiducial-focus-augmentation-for-facial","paper_url":"https://arxiv.org/abs/2402.15044v1","paper_title":"Fiducial Focus Augmentation for Facial Landmark Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"SH-FAN","metrics":{"NME (inter-ocular)":"3.02%"},"uses_additional_data":true,"paper_date":"2021-11-03","paper":"/paper/subpixel-heatmap-regression-for-facial","paper_url":"https://arxiv.org/abs/2111.02360v1","paper_title":"Subpixel Heatmap Regression for Facial Landmark Localization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"DTLD+","metrics":{"NME (inter-ocular)":"3.02%"},"uses_additional_data":false,"paper_date":"2022-08-23","paper":"/paper/towards-accurate-facial-landmark-detection-1","paper_url":"https://arxiv.org/abs/2208.10808v1","paper_title":"Towards Accurate Facial Landmark Detection via Cascaded Transformers","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"PIPNet (ResNet-101)","metrics":{"NME (inter-ocular)":"3.08%"},"uses_additional_data":false,"paper_date":"2020-03-08","paper":"/paper/pixel-in-pixel-net-towards-efficient-facial","paper_url":"https://arxiv.org/abs/2003.03771v3","paper_title":"Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild","code":"https://github.com/jhb86253817/PIPNet","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":15,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"BarrelNet (ResNet-101)","metrics":{"NME (inter-ocular)":"3.1%"},"uses_additional_data":false,"paper_date":"2021-05-27","paper":"/paper/when-liebig-s-barrel-meets-facial-landmark","paper_url":"https://arxiv.org/abs/2105.13150v2","paper_title":"When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"STAR","metrics":{"NME (inter-ocular)":"3.21%","NME (inter-pupil)":"4.62"},"uses_additional_data":false,"paper_date":"2023-06-05","paper":"/paper/star-loss-reducing-semantic-ambiguity-in-1","paper_url":"https://arxiv.org/abs/2306.02763v1","paper_title":"STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection","code":"https://github.com/zhenglinzhou/star","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":7,"model":"HIH","metrics":{"NME (inter-ocular)":"3.21%"},"uses_additional_data":false,"paper_date":"2021-04-07","paper":"/paper/hih-towards-more-accurate-face-alignment-via","paper_url":"https://arxiv.org/abs/2104.03100v2","paper_title":"HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap","code":"https://github.com/starhiking/HeatmapInHeatmap","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"HIH w. MSE(2 stack)","metrics":{"NME (inter-ocular)":"3.28%"},"uses_additional_data":false,"paper_date":"2021-09-13","paper":"/paper/revisiting-quantization-error-in-face","paper_url":"https://openaccess.thecvf.com/content/ICCV2021W/MFR/html/Lan_Revisting_Quantization_Error_in_Face_Alignment_ICCVW_2021_paper.html","paper_title":"Revisiting Quantization Error in Face Alignment","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"SLPT","metrics":{"NME (inter-ocular)":"3.32","NME (inter-pupil)":"4.79"},"uses_additional_data":false,"paper_date":"2022-03-13","paper":"/paper/sparse-local-patch-transformer-for-robust","paper_url":"https://arxiv.org/abs/2203.06541v2","paper_title":"Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning","code":"https://github.com/jiahao-uts/slpt-master","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"Ours (VGG-F)","metrics":{"NME (inter-ocular)":"3.32"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/pre-training-strategies-and-datasets-for","paper_url":"https://arxiv.org/abs/2103.16554v2","paper_title":"Pre-training strategies and datasets for facial representation learning","code":"https://github.com/tomas-gajarsky/facetorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":11,"model":"ATF","metrics":{"NME (inter-ocular)":"3.32%"},"uses_additional_data":true,"paper_date":"2020-10-12","paper":"/paper/atf-towards-robust-face-alignment-via","paper_url":"https://dl.acm.org/doi/10.1145/3394171.3414037","paper_title":"ATF: Towards Robust Face Alignment via Leveraging Similarity and Diversity across Different Datasets","code":"https://github.com/starhiking/ATF","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"HRNet","metrics":{"NME (inter-ocular)":"3.45%"},"uses_additional_data":false,"paper_date":"2019-04-09","paper":"/paper/high-resolution-representations-for-labeling","paper_url":"http://arxiv.org/abs/1904.04514v1","paper_title":"High-Resolution Representations for Labeling Pixels and Regions","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":39,"syntology":{"n_ran":3,"n_unverified":15,"n_samples":18,"n_pointer_only_licence":5}},{"rank_in_archive_order":13,"model":"HRNet","metrics":{"NME (inter-ocular)":"3.45"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"syntology":{"n_ran":3,"n_unverified":31,"n_samples":34,"n_pointer_only_licence":16}},{"rank_in_archive_order":14,"model":"EF-3ACR","metrics":{"NME (inter-ocular)":"3.47%"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/acr-loss-adaptive-coordinate-based-regression","paper_url":"https://arxiv.org/abs/2203.15835v2","paper_title":"ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignment","code":"https://github.com/aliprf/acr-loss","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"SCC","metrics":{"NME (inter-ocular)":"3.63%"},"uses_additional_data":false,"paper_date":"2020-06-21","paper":"/paper/fast-and-accurate-structure-coherence","paper_url":"https://arxiv.org/abs/2006.11697v1","paper_title":"Fast and Accurate: Structure Coherence Component for Face Alignment","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"PropNet","metrics":{"NME (inter-ocular)":"3.71%"},"uses_additional_data":false,"paper_date":"2020-06-25","paper":"/paper/propagationnet-propagate-points-to-curve-to-1","paper_url":"https://arxiv.org/abs/2006.14308v1","paper_title":"PropagationNet: Propagate Points to Curve to Learn Structure Information","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"EfficientNet","metrics":{"NME (inter-ocular)":"3.81%"},"uses_additional_data":false,"paper_date":"2021-11-13","paper":"/paper/facial-landmark-points-detection-using","paper_url":"https://arxiv.org/abs/2111.07047v1","paper_title":"Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks","code":"https://github.com/aliprf/kd-loss","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"LAB (w/ B)","metrics":{"NME (inter-ocular)":"3.92%"},"uses_additional_data":false,"paper_date":"2018-05-26","paper":"/paper/look-at-boundary-a-boundary-aware-face","paper_url":"http://arxiv.org/abs/1805.10483v1","paper_title":"Look at Boundary: A Boundary-Aware Face Alignment Algorithm","code":"https://github.com/open-mmlab/mmpose","n_code_links":2,"syntology":null},{"rank_in_archive_order":19,"model":"MobileNetV2+KD-Loss","metrics":{"NME (inter-ocular)":"4.11%"},"uses_additional_data":false,"paper_date":"2021-11-13","paper":"/paper/facial-landmark-points-detection-using","paper_url":"https://arxiv.org/abs/2111.07047v1","paper_title":"Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks","code":"https://github.com/aliprf/kd-loss","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"Wing (Feng et al., 2018)","metrics":{"NME (inter-ocular)":"5.07"},"uses_additional_data":false,"paper_date":"2017-11-17","paper":"/paper/wing-loss-for-robust-facial-landmark","paper_url":"http://arxiv.org/abs/1711.06753v5","paper_title":"Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks","code":"https://github.com/open-mmlab/mmpose","n_code_links":6,"syntology":null},{"rank_in_archive_order":21,"model":"LAB","metrics":{"NME (inter-ocular)":"5.58%"},"uses_additional_data":false,"paper_date":"2018-05-26","paper":"/paper/look-at-boundary-a-boundary-aware-face","paper_url":"http://arxiv.org/abs/1805.10483v1","paper_title":"Look at Boundary: A Boundary-Aware Face Alignment Algorithm","code":"https://github.com/open-mmlab/mmpose","n_code_links":2,"syntology":null},{"rank_in_archive_order":22,"model":"PCD-CNNCVPR 18","metrics":{"NME (inter-ocular)":"5.77%"},"uses_additional_data":false,"paper_date":"2018-02-19","paper":"/paper/disentangling-3d-pose-in-a-dendritic-cnn-for","paper_url":"http://arxiv.org/abs/1802.06713v3","paper_title":"Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"MNN+OR (Inter-pupils Norm)","metrics":{"NME (inter-pupil)":"5.04%","Recall at 80% precision (Landmarks Visibility)":"72.12"},"uses_additional_data":false,"paper_date":"2020-12-22","paper":"/paper/multi-task-head-pose-estimation-in-the-wild-1","paper_url":"https://arxiv.org/abs/2202.02299v1","paper_title":"Multi-task head pose estimation in-the-wild","code":"https://github.com/bobetocalo/bobetocalo_pami20","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"3DDE (Inter-pupil Norm)","metrics":{"NME (inter-pupil)":"5.11%","Recall at 80% precision (Landmarks Visibility)":"63.89"},"uses_additional_data":false,"paper_date":"2019-02-05","paper":"/paper/face-alignment-using-a-3d-deeply-initialized","paper_url":"https://arxiv.org/abs/1902.01831v2","paper_title":"Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees","code":"https://github.com/bobetocalo/bobetocalo_eccv18","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"CHR2C (Inter-pupils Norm)","metrics":{"NME (inter-pupil)":"5.09%"},"uses_additional_data":false,"paper_date":"2019-10-15","paper":"/paper/cascade-of-encoder-decoder-cnns-with-learned","paper_url":"https://doi.org/10.1016/j.patrec.2019.10.012","paper_title":"Cascade of Encoder-Decoder CNNs with Learned Coordinates Regressor for Robust Facial Landmarks Detection","code":"https://github.com/bobetocalo/bobetocalo_prl19","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"DCFE","metrics":{"NME (inter-pupil)":"5.27%"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/a-deeply-initialized-coarse-to-fine-ensemble","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Roberto_Valle_A_Deeply-initialized_Coarse-to-fine_ECCV_2018_paper.html","paper_title":"A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment","code":"https://github.com/bobetocalo/bobetocalo_eccv18","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"DenseU-Net + Dual Transformer","metrics":{"NME (inter-pupil)":"5.55%"},"uses_additional_data":false,"paper_date":"2018-12-05","paper":"/paper/stacked-dense-u-nets-with-dual-transformers","paper_url":"http://arxiv.org/abs/1812.01936v1","paper_title":"Stacked Dense U-Nets with Dual Transformers for Robust Face Alignment","code":"https://github.com/deepinsight/insightface","n_code_links":3,"syntology":null},{"rank_in_archive_order":28,"model":"MNN (Inter-pupil Norm)","metrics":{"NME (inter-pupil)":"5.65%"},"uses_additional_data":false,"paper_date":"2020-12-22","paper":"/paper/multi-task-head-pose-estimation-in-the-wild-1","paper_url":"https://arxiv.org/abs/2202.02299v1","paper_title":"Multi-task head pose estimation in-the-wild","code":"https://github.com/bobetocalo/bobetocalo_pami20","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":12,"n_unverified":61,"n_samples":73,"n_pointer_only_licence":25,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":12,"n_unverified":61,"n_samples":73,"n_pointer_only_licence":25,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}