{"url":"/sota/monocular-3d-human-pose-estimation-on-human3","task":{"name":"Monocular 3D Human Pose Estimation","url":"/task/monocular-3d-human-pose-estimation","note":null},"dataset":{"name":"Human3.6M","url":"/dataset/human3-6m"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"This task targets at 3D human pose estimation with a single RGB camera.","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":["Average MPJPE (mm)","Use Video Sequence","Frames Needed","Need Ground Truth 2D Pose","PA-MPJPE","2D detector"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average MPJPE (mm)":null,"Use Video Sequence":null,"Frames Needed":null,"Need Ground Truth 2D Pose":null,"PA-MPJPE":null,"2D detector":null}},"counts":{"rows":52,"rows_with_code":45,"rows_with_paper_page":52,"rows_dated":52,"rows_using_additional_data":4},"rows":[{"rank_in_archive_order":1,"model":"MotionBERT (Finetune)","metrics":{"2D detector":"SH","Average MPJPE (mm)":"37.5","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":true,"paper_date":"2022-10-12","paper":"/paper/motionbert-unified-pretraining-for-human","paper_url":"https://arxiv.org/abs/2210.06551v5","paper_title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","code":"https://github.com/Walter0807/MotionBERT","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"MotionAGFormer-L","metrics":{"2D detector":"SH","Average MPJPE (mm)":"38.4","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2023-10-25","paper":"/paper/motionagformer-enhancing-3d-human-pose","paper_url":"https://arxiv.org/abs/2310.16288v1","paper_title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","code":"https://github.com/taatiteam/motionagformer","n_code_links":1,"syntology":{"n_ran":14,"n_unverified":2,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"MotionAGFormer-B","metrics":{"2D detector":"SH","Average MPJPE (mm)":"38.4","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2023-10-25","paper":"/paper/motionagformer-enhancing-3d-human-pose","paper_url":"https://arxiv.org/abs/2310.16288v1","paper_title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","code":"https://github.com/taatiteam/motionagformer","n_code_links":1,"syntology":{"n_ran":14,"n_unverified":2,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"MotionBERT (Scratch)","metrics":{"2D detector":"SH","Average MPJPE (mm)":"39.2","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/motionbert-unified-pretraining-for-human","paper_url":"https://arxiv.org/abs/2210.06551v5","paper_title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","code":"https://github.com/Walter0807/MotionBERT","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"D3DP","metrics":{"2D detector":"CPN","Average MPJPE (mm)":"39.5","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2023-03-21","paper":"/paper/diffusion-based-3d-human-pose-estimation-with","paper_url":"https://arxiv.org/abs/2303.11579v2","paper_title":"Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation","code":"https://github.com/patrick-swk/d3dp","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"DDHPose","metrics":{"2D detector":"CPN","Average MPJPE (mm)":"39.7","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2024-03-07","paper":"/paper/disentangled-diffusion-based-3d-human-pose","paper_url":"https://arxiv.org/abs/2403.04444v1","paper_title":"Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser","code":"https://github.com/Andyen512/DDHPose","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"MixSTE (HRNet, T=243)","metrics":{"2D detector":"HRNet","Average MPJPE (mm)":"39.8","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2022-03-02","paper":"/paper/mixste-seq2seq-mixed-spatio-temporal-encoder","paper_url":"https://arxiv.org/abs/2203.00859v4","paper_title":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","code":"https://github.com/JinluZhang1126/MixSTE","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":8,"model":"HEMlets Pose (H36M+MPII)","metrics":{"Average MPJPE (mm)":"39.9","Frames Needed":"1","PA-MPJPE":"27.9"},"uses_additional_data":false,"paper_date":"2019-10-26","paper":"/paper/hemlets-pose-learning-part-centric-heatmap-1","paper_url":"https://arxiv.org/abs/1910.12032v1","paper_title":"HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"Spatio-Temporal Network (T=128)","metrics":{"Average MPJPE (mm)":"40.1","Frames Needed":"128","Need Ground Truth 2D Pose":"No","PA-MPJPE":"30.7","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2020-04-07","paper":"/paper/3d-human-pose-estimation-using-spatio-1","paper_url":"https://arxiv.org/abs/2004.11822v1","paper_title":"3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"KTPFormer","metrics":{"2D detector":"CPN","Average MPJPE (mm)":"40.1","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2024-03-31","paper":"/paper/ktpformer-kinematics-and-trajectory-prior","paper_url":"https://arxiv.org/abs/2404.00658v2","paper_title":"KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation","code":"https://github.com/JihuaPeng/KTPFormer","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":11,"model":"GenHMR","metrics":{"Average MPJPE (mm)":"41.2","PA-MPJPE":"29.8"},"uses_additional_data":false,"paper_date":"2024-12-19","paper":"/paper/genhmr-generative-human-mesh-recovery","paper_url":"https://arxiv.org/abs/2412.14444v1","paper_title":"GenHMR: Generative Human Mesh Recovery","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"P-STMO (N=243)","metrics":{"2D detector":"CPN","Average MPJPE (mm)":"42.1","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2022-03-15","paper":"/paper/p-stmo-pre-trained-spatial-temporal-many-to","paper_url":"https://arxiv.org/abs/2203.07628v2","paper_title":"P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation","code":"https://github.com/patrick-swk/p-stmo","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":1}},{"rank_in_archive_order":13,"model":"MotionAGFormer-S","metrics":{"2D detector":"SH","Average MPJPE (mm)":"42.5","Frames Needed":"81","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2023-10-25","paper":"/paper/motionagformer-enhancing-3d-human-pose","paper_url":"https://arxiv.org/abs/2310.16288v1","paper_title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","code":"https://github.com/taatiteam/motionagformer","n_code_links":1,"syntology":{"n_ran":14,"n_unverified":2,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Anatomy3D","metrics":{"2D detector":"CPN","Average MPJPE (mm)":"44.1","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2020-02-24","paper":"/paper/anatomy-aware-3d-human-pose-estimation-in","paper_url":"https://arxiv.org/abs/2002.10322v5","paper_title":"Anatomy-aware 3D Human Pose Estimation with Bone-based Pose Decomposition","code":"https://github.com/sunnychencool/Anatomy3D","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"PoseFormer (T=81)","metrics":{"2D detector":"CPN","Average MPJPE (mm)":"44.3","Frames Needed":"81"},"uses_additional_data":false,"paper_date":"2021-03-18","paper":"/paper/3d-human-pose-estimation-with-spatial-and","paper_url":"https://arxiv.org/abs/2103.10455v3","paper_title":"3D Human Pose Estimation with Spatial and Temporal Transformers","code":"https://github.com/zczcwh/PoseFormer","n_code_links":3,"syntology":{"n_ran":4,"n_unverified":4,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":16,"model":"RIE (T=243 CPN)","metrics":{"2D detector":"CPN","Average MPJPE (mm)":"44.3","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2021-07-29","paper":"/paper/improving-robustness-and-accuracy-via","paper_url":"https://arxiv.org/abs/2107.13994v1","paper_title":"Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation","code":"https://github.com/paTRICK-swk/Pose3D-RIE","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"MotionAGFormer-XS","metrics":{"2D detector":"SH","Average MPJPE (mm)":"45.1","Frames Needed":"27","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2023-10-25","paper":"/paper/motionagformer-enhancing-3d-human-pose","paper_url":"https://arxiv.org/abs/2310.16288v1","paper_title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","code":"https://github.com/taatiteam/motionagformer","n_code_links":1,"syntology":{"n_ran":14,"n_unverified":2,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"Attention3DHumanPose","metrics":{"2D detector":"CPN","Average MPJPE (mm)":"45.1","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/attention-mechanism-exploits-temporal","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Liu_Attention_Mechanism_Exploits_Temporal_Contexts_Real-Time_3D_Human_Pose_Reconstruction_CVPR_2020_paper.html","paper_title":"Attention Mechanism Exploits Temporal Contexts: Real-Time 3D Human Pose Reconstruction","code":"https://github.com/lrxjason/Attention3DHumanPose","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"Trajectory Space Factorization (50 frames)","metrics":{"Average MPJPE (mm)":"46.6","Frames Needed":"50","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2019-08-22","paper":"/paper/trajectory-space-factorization-for-deep-video","paper_url":"https://arxiv.org/abs/1908.08289v1","paper_title":"Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation","code":"https://github.com/jiahaoLjh/trajectory-pose-3d","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"VideoPose3D (T=243)","metrics":{"2D detector":"CPN","Average MPJPE (mm)":"46.8","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2018-11-28","paper":"/paper/3d-human-pose-estimation-in-video-with","paper_url":"http://arxiv.org/abs/1811.11742v2","paper_title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","code":"https://github.com/open-mmlab/mmpose","n_code_links":10,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":21,"model":"PointHMR","metrics":{"Average MPJPE (mm)":"48.3","PA-MPJPE":"32.9"},"uses_additional_data":true,"paper_date":"2023-04-19","paper":"/paper/sampling-is-matter-point-guided-3d-human-mesh-1","paper_url":"https://arxiv.org/abs/2304.09502v1","paper_title":"Sampling is Matter: Point-guided 3D Human Mesh Reconstruction","code":"https://github.com/DCVL-3D/PointHMR_release","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"SRNET","metrics":{"Average MPJPE (mm)":"49.9","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2020-07-18","paper":"/paper/srnet-improving-generalization-in-3d-human","paper_url":"https://arxiv.org/abs/2007.09389v1","paper_title":"SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach","code":"https://github.com/ailingzengzzz/Split-and-Recombine-Net","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":8,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"HR-Net+VPose+PoseAug","metrics":{"Average MPJPE (mm)":"50.2","PA-MPJPE":"39.1"},"uses_additional_data":false,"paper_date":"2021-05-06","paper":"/paper/poseaug-a-differentiable-pose-augmentation","paper_url":"https://arxiv.org/abs/2105.02465v1","paper_title":"PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation","code":"https://github.com/jfzhang95/PoseAug","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"TAG-Net","metrics":{"Average MPJPE (mm)":"50.9","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2020-06-14","paper":"/paper/cascaded-deep-monocular-3d-human-pose-1","paper_url":"https://arxiv.org/abs/2006.07778v3","paper_title":"Cascaded deep monocular 3D human pose estimation with evolutionary training data","code":"https://github.com/Nicholasli1995/EvoSkeleton","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"cross-dataset-evaluation","metrics":{"Average MPJPE (mm)":"52.0","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":true,"paper_date":"2020-04-07","paper":"/paper/predicting-camera-viewpoint-improves-cross","paper_url":"https://arxiv.org/abs/2004.03143v1","paper_title":"Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"TP-Net","metrics":{"Average MPJPE (mm)":"52.1","Frames Needed":"20","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2017-11-25","paper":"/paper/learning-3d-human-pose-from-structure-and","paper_url":"http://arxiv.org/abs/1711.09250v2","paper_title":"Learning 3D Human Pose from Structure and Motion","code":"https://github.com/anuragmundhada/3dpose-demo-iitb","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"Multimodal Mixture Density Networks","metrics":{"Average MPJPE (mm)":"52.7","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2019-04-11","paper":"/paper/generating-multiple-hypotheses-for-3d-human","paper_url":"http://arxiv.org/abs/1904.05547v1","paper_title":"Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network","code":"https://github.com/chaneyddtt/Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"SemGCN","metrics":{"Average MPJPE (mm)":"57.6","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2019-04-06","paper":"/paper/semantic-graph-convolutional-networks-for-3d","paper_url":"https://arxiv.org/abs/1904.03345v3","paper_title":"Semantic Graph Convolutional Networks for 3D Human Pose Regression","code":"https://github.com/garyzhao/SemGCN","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"MultiPoseNet","metrics":{"Average MPJPE (mm)":"58.0","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/monocular-3d-human-pose-estimation-by-1","paper_url":"https://arxiv.org/abs/1904.01324v2","paper_title":"Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking","code":"https://github.com/ssfootball04/generative_pose","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"Monocular Total Capture","metrics":{"Average MPJPE (mm)":"58.3","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"NO"},"uses_additional_data":false,"paper_date":"2018-12-04","paper":"/paper/monocular-total-capture-posing-face-body-and","paper_url":"http://arxiv.org/abs/1812.01598v1","paper_title":"Monocular Total Capture: Posing Face, Body, and Hands in the Wild","code":"https://github.com/CMU-Perceptual-Computing-Lab/MonocularTotalCapture","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"SIM (SH detections FT) (MA)","metrics":{"Average MPJPE (mm)":"62.9","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2017-05-08","paper":"/paper/a-simple-yet-effective-baseline-for-3d-human","paper_url":"http://arxiv.org/abs/1705.03098v2","paper_title":"A simple yet effective baseline for 3d human pose estimation","code":"https://github.com/open-mmlab/mmpose","n_code_links":14,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"Bundle Adjustment (GTi)","metrics":{"Average MPJPE (mm)":"63.3"},"uses_additional_data":false,"paper_date":"2019-05-10","paper":"/paper/exploiting-temporal-context-for-3d-human-pose","paper_url":"https://arxiv.org/abs/1905.04266v1","paper_title":"Exploiting temporal context for 3D human pose estimation in the wild","code":"https://github.com/deepmind/Temporal-3D-Pose-Kinetics","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"SelecSLS","metrics":{"Average MPJPE (mm)":"63.6","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2019-07-01","paper":"/paper/xnect-real-time-multi-person-3d-human-pose","paper_url":"https://arxiv.org/abs/1907.00837v2","paper_title":"XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":4,"syntology":null},{"rank_in_archive_order":34,"model":"Weakly Supervised Transfer Learning","metrics":{"Average MPJPE (mm)":"64.9","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2017-04-08","paper":"/paper/towards-3d-human-pose-estimation-in-the-wild","paper_url":"http://arxiv.org/abs/1704.02447v2","paper_title":"Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach","code":"https://github.com/xingyizhou/pytorch-pose-hg-3d","n_code_links":6,"syntology":null},{"rank_in_archive_order":35,"model":"VIBE","metrics":{"Average MPJPE (mm)":"65.6","Frames Needed":"16","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2019-12-11","paper":"/paper/vibe-video-inference-for-human-body-pose-and","paper_url":"https://arxiv.org/abs/1912.05656v3","paper_title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","code":"https://github.com/mkocabas/VIBE","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":36,"model":"GraphCMR","metrics":{"Average MPJPE (mm)":"74.7","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2019-05-08","paper":"/paper/convolutional-mesh-regression-for-single","paper_url":"https://arxiv.org/abs/1905.03244v1","paper_title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","code":"https://github.com/nkolot/GraphCMR","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"Projected-pose belief maps + 2D fusion layers","metrics":{"Average MPJPE (mm)":"88.39","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2017-01-01","paper":"/paper/lifting-from-the-deep-convolutional-3d-pose","paper_url":"http://arxiv.org/abs/1701.00295v4","paper_title":"Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image","code":"https://github.com/DenisTome/Lifting-from-the-Deep-release","n_code_links":11,"syntology":null},{"rank_in_archive_order":38,"model":"RepNet","metrics":{"Average MPJPE (mm)":"89.9","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2019-02-26","paper":"/paper/repnet-weakly-supervised-training-of-an","paper_url":"http://arxiv.org/abs/1902.09868v2","paper_title":"RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation","code":"https://github.com/bastianwandt/RepNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"Dual-source approach","metrics":{"Average MPJPE (mm)":"97.39","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2017-05-08","paper":"/paper/a-dual-source-approach-for-3d-human-pose","paper_url":"http://arxiv.org/abs/1705.02883v2","paper_title":"A Dual-Source Approach for 3D Human Pose Estimation from a Single Image","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":40,"model":"Sparseness Meets Deepness","metrics":{"Average MPJPE (mm)":"113.01","Frames Needed":"300","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2015-11-30","paper":"/paper/sparseness-meets-deepness-3d-human-pose","paper_url":"http://arxiv.org/abs/1511.09439v2","paper_title":"Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video","code":"https://github.com/chuxiaoselena/SparsenessMeetsDeepness","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"HMR","metrics":{"Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2017-12-18","paper":"/paper/end-to-end-recovery-of-human-shape-and-pose","paper_url":"http://arxiv.org/abs/1712.06584v2","paper_title":"End-to-end Recovery of Human Shape and Pose","code":"https://github.com/open-mmlab/mmpose","n_code_links":10,"syntology":null},{"rank_in_archive_order":42,"model":"Neural Body Fitting\n(NBF)","metrics":{"Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2018-08-17","paper":"/paper/neural-body-fitting-unifying-deep-learning","paper_url":"http://arxiv.org/abs/1808.05942v1","paper_title":"Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation","code":"https://github.com/andrewjong/SwapNet","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":43,"model":"SMPLify\n(dense)","metrics":{"Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2017-01-10","paper":"/paper/unite-the-people-closing-the-loop-between-3d","paper_url":"http://arxiv.org/abs/1701.02468v3","paper_title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","code":"https://github.com/MandyMo/pytorch_HMR","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":44,"model":"Ordinal Depth Supervision","metrics":{"Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2018-05-10","paper":"/paper/ordinal-depth-supervision-for-3d-human-pose","paper_url":"http://arxiv.org/abs/1805.04095v1","paper_title":"Ordinal Depth Supervision for 3D Human Pose Estimation","code":"https://github.com/geopavlakos/ordinal-pose3d","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"Adversarial Learning","metrics":{"Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2018-03-26","paper":"/paper/3d-human-pose-estimation-in-the-wild-by","paper_url":"http://arxiv.org/abs/1803.09722v2","paper_title":"3D Human Pose Estimation in the Wild by Adversarial Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":46,"model":"Moon et. al.","metrics":{"Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2019-07-26","paper":"/paper/camera-distance-aware-top-down-approach-for","paper_url":"https://arxiv.org/abs/1907.11346v2","paper_title":"Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image","code":"https://github.com/mks0601/3DMPPE_POSENET_RELEASE","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":47,"model":"PoseAug","metrics":{"Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false,"paper_date":"2021-05-06","paper":"/paper/poseaug-a-differentiable-pose-augmentation","paper_url":"https://arxiv.org/abs/2105.02465v1","paper_title":"PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation","code":"https://github.com/jfzhang95/PoseAug","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"HEMlets Pose","metrics":{"Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":true,"paper_date":"2019-10-26","paper":"/paper/hemlets-pose-learning-part-centric-heatmap-1","paper_url":"https://arxiv.org/abs/1910.12032v1","paper_title":"HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":49,"model":"Ray3D","metrics":{"Frames Needed":"9","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/ray3d-ray-based-3d-human-pose-estimation-for","paper_url":"https://arxiv.org/abs/2203.11471v3","paper_title":"Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization","code":"https://github.com/YxZhxn/Ray3D","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"Bundle Adjustment","metrics":{"Frames Needed":"190","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false,"paper_date":"2019-05-10","paper":"/paper/exploiting-temporal-context-for-3d-human-pose","paper_url":"https://arxiv.org/abs/1905.04266v1","paper_title":"Exploiting temporal context for 3D human pose estimation in the wild","code":"https://github.com/deepmind/Temporal-3D-Pose-Kinetics","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":51,"model":"Neural Body Fitting (NBF)","metrics":{"PA-MPJPE":"59.9"},"uses_additional_data":false,"paper_date":"2018-08-17","paper":"/paper/neural-body-fitting-unifying-deep-learning","paper_url":"http://arxiv.org/abs/1808.05942v1","paper_title":"Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation","code":"https://github.com/andrewjong/SwapNet","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":52,"model":"SMPLify (dense)","metrics":{"PA-MPJPE":"80.7"},"uses_additional_data":false,"paper_date":"2017-01-10","paper":"/paper/unite-the-people-closing-the-loop-between-3d","paper_url":"http://arxiv.org/abs/1701.02468v3","paper_title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","code":"https://github.com/MandyMo/pytorch_HMR","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}}],"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 6,264 of the 9,581 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":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":29,"rows_with_any_sample_ran":23,"distinct_papers_with_graph_line":22,"distinct_papers_with_any_sample_ran":17,"samples_over_distinct_papers":{"n_ran":67,"n_unverified":70,"n_samples":137,"n_pointer_only_licence":28,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":116,"n_unverified":85,"n_samples":201,"n_pointer_only_licence":30,"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"}}}