{"url":"/sota/3d-face-reconstruction-on-florence","task":{"name":"3D Face Reconstruction","url":"/task/3d-face-reconstruction","note":null},"dataset":{"name":"Florence","url":"/dataset/florence"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**3D Face Reconstruction** is a computer vision task that involves creating a 3D model of a human face from a 2D image or a set of images. The goal of 3D face reconstruction is to reconstruct a digital 3D representation of a person's face, which can be used for various applications such as animation, virtual reality, and biometric identification.\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":["Mean NME ","Average 3D Error","RMSE Cooperative","RMSE Indoor","RMSE Outdoor","Mean NME"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean NME ":null,"Average 3D Error":"lower","RMSE Cooperative":"lower","RMSE Indoor":"lower","RMSE Outdoor":"lower","Mean NME":null}},"counts":{"rows":16,"rows_with_code":10,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PRN","metrics":{"Mean NME ":"3.7551%"},"uses_additional_data":false,"paper_date":"2018-03-21","paper":"/paper/joint-3d-face-reconstruction-and-dense","paper_url":"http://arxiv.org/abs/1803.07835v1","paper_title":"Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network","code":"https://github.com/YadiraF/PRNet","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"VRN-Guided","metrics":{"Mean NME ":"5.2667%"},"uses_additional_data":false,"paper_date":"2017-03-22","paper":"/paper/large-pose-3d-face-reconstruction-from-a","paper_url":"http://arxiv.org/abs/1703.07834v2","paper_title":"Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression","code":"https://github.com/AaronJackson/vrn","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"3DDFA","metrics":{"Mean NME ":"6.3833%"},"uses_additional_data":false,"paper_date":"2015-11-23","paper":"/paper/face-alignment-across-large-poses-a-3d","paper_url":"http://arxiv.org/abs/1511.07212v1","paper_title":"Face Alignment Across Large Poses: A 3D Solution","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"GANFit","metrics":{"Average 3D Error":"0.95"},"uses_additional_data":false,"paper_date":"2019-02-15","paper":"/paper/ganfit-generative-adversarial-network-fitting","paper_url":"http://arxiv.org/abs/1902.05978v2","paper_title":"GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction","code":"https://github.com/barisgecer/ganfit","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Unsupervised-3DMMR","metrics":{"Average 3D Error":"1.50"},"uses_additional_data":false,"paper_date":"2018-06-15","paper":"/paper/unsupervised-training-for-3d-morphable-model","paper_url":"http://arxiv.org/abs/1806.06098v1","paper_title":"Unsupervised Training for 3D Morphable Model Regression","code":"https://github.com/google/tf_mesh_renderer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":13,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"itwmm","metrics":{"Average 3D Error":"1.82"},"uses_additional_data":false,"paper_date":"2017-01-19","paper":"/paper/3d-face-morphable-models-in-the-wild","paper_url":"http://arxiv.org/abs/1701.05360v1","paper_title":"3D Face Morphable Models \"In-the-Wild\"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"3DMM-CNN","metrics":{"Average 3D Error":"1.93"},"uses_additional_data":false,"paper_date":"2016-12-15","paper":"/paper/regressing-robust-and-discriminative-3d","paper_url":"http://arxiv.org/abs/1612.04904v1","paper_title":"Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network","code":"https://github.com/anhttran/3dmm_cnn","n_code_links":5,"syntology":null},{"rank_in_archive_order":8,"model":"ASM","metrics":{"RMSE Cooperative":"1.34","RMSE Indoor":"1.53"},"uses_additional_data":false,"paper_date":"2023-04-19","paper":"/paper/asm-adaptive-skinning-model-for-high-quality","paper_url":"https://arxiv.org/abs/2304.09423v3","paper_title":"ASM: Adaptive Skinning Model for High-Quality 3D Face Modeling","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"DenseLandmarks (Multi-view)","metrics":{"RMSE Cooperative":"1.43","RMSE Indoor":"1.42","RMSE Outdoor":"1.42"},"uses_additional_data":false,"paper_date":"2022-04-06","paper":"/paper/3d-face-reconstruction-with-dense-landmarks","paper_url":"https://arxiv.org/abs/2204.02776v2","paper_title":"3D face reconstruction with dense landmarks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"Deng","metrics":{"RMSE Cooperative":"1.60","RMSE Indoor":"1.61"},"uses_additional_data":false,"paper_date":"2019-03-20","paper":"/paper/accurate-3d-face-reconstruction-with-weakly","paper_url":"https://arxiv.org/abs/1903.08527v2","paper_title":"Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set","code":"https://github.com/Microsoft/Deep3DFaceReconstruction","n_code_links":4,"syntology":{"n_ran":15,"n_unverified":21,"n_samples":36,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"DenseLandmarks (Single-view)","metrics":{"RMSE Cooperative":"1.64","RMSE Indoor":"1.62","RMSE Outdoor":"1.61"},"uses_additional_data":false,"paper_date":"2022-04-06","paper":"/paper/3d-face-reconstruction-with-dense-landmarks","paper_url":"https://arxiv.org/abs/2204.02776v2","paper_title":"3D face reconstruction with dense landmarks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Deep3DFaceReconstruction","metrics":{"RMSE Cooperative":"1.66","RMSE Indoor":"1.66","RMSE Outdoor":"1.69"},"uses_additional_data":false,"paper_date":"2019-03-20","paper":"/paper/accurate-3d-face-reconstruction-with-weakly","paper_url":"https://arxiv.org/abs/1903.08527v2","paper_title":"Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set","code":"https://github.com/Microsoft/Deep3DFaceReconstruction","n_code_links":4,"syntology":{"n_ran":15,"n_unverified":21,"n_samples":36,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"Piotraschke and Blanz","metrics":{"RMSE Cooperative":"1.68","RMSE Indoor":"1.67"},"uses_additional_data":false,"paper_date":"2016-06-01","paper":"/paper/automated-3d-face-reconstruction-from","paper_url":"http://openaccess.thecvf.com/content_cvpr_2016/html/Piotraschke_Automated_3D_Face_CVPR_2016_paper.html","paper_title":"Automated 3D Face Reconstruction From Multiple Images Using Quality Measures","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"Genova et al.","metrics":{"RMSE Cooperative":"1.78","RMSE Indoor":"1.78","RMSE Outdoor":"1.76"},"uses_additional_data":false,"paper_date":"2018-06-15","paper":"/paper/unsupervised-training-for-3d-morphable-model","paper_url":"http://arxiv.org/abs/1806.06098v1","paper_title":"Unsupervised Training for 3D Morphable Model Regression","code":"https://github.com/google/tf_mesh_renderer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":13,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"Tran et al.","metrics":{"RMSE Cooperative":"1.97","RMSE Indoor":"2.03","RMSE Outdoor":"1.93"},"uses_additional_data":false,"paper_date":"2016-12-15","paper":"/paper/regressing-robust-and-discriminative-3d","paper_url":"http://arxiv.org/abs/1612.04904v1","paper_title":"Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network","code":"https://github.com/anhttran/3dmm_cnn","n_code_links":5,"syntology":null},{"rank_in_archive_order":16,"model":"3DDFA_V2","metrics":{"Mean NME":"3.56"},"uses_additional_data":false,"paper_date":"2020-09-21","paper":"/paper/towards-fast-accurate-and-stable-3d-dense-1","paper_url":"https://arxiv.org/abs/2009.09960v2","paper_title":"Towards Fast, Accurate and Stable 3D Dense Face Alignment","code":"https://github.com/cleardusk/3DDFA","n_code_links":3,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":3}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,821 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":6,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":21,"n_unverified":48,"n_samples":69,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":36,"n_unverified":82,"n_samples":118,"n_pointer_only_licence":3,"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"}}}