{"url":"/sota/3d-human-pose-estimation-on-3dpw","task":{"name":"3D Human Pose Estimation","url":"/task/3d-human-pose-estimation","note":null},"dataset":{"name":"3DPW","url":"/dataset/3dpw"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**3D Human Pose Estimation** is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.","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":["MPVPE","PA-MPJPE","MPJPE","Acceleration Error","FLOPs (G)","Number of parameters (M)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"MPVPE":null,"PA-MPJPE":null,"MPJPE":null,"Acceleration Error":"lower","FLOPs (G)":"lower","Number of parameters (M)":null}},"counts":{"rows":119,"rows_with_code":78,"rows_with_paper_page":119,"rows_dated":119,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ExtPose (-a, T=16)","metrics":{"MPJPE":"54.2","MPVPE":"67.5","PA-MPJPE":"34.0"},"uses_additional_data":false,"paper_date":"2025-06-18","paper":"/paper/extpose-robust-and-coherent-pose-estimation","paper_url":"https://openreview.net/forum?id=hm9FNEZZ6z","paper_title":"ExtPose: Robust and Coherent Pose Estimation by Extending ViTs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"WHAM (ViT)","metrics":{"MPJPE":"57.8","MPVPE":"68.7","PA-MPJPE":"35.9"},"uses_additional_data":false,"paper_date":"2023-12-12","paper":"/paper/wham-reconstructing-world-grounded-humans","paper_url":"https://arxiv.org/abs/2312.07531v2","paper_title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","code":"https://github.com/yohanshin/WHAM","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":4,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"TAR (N=9)","metrics":{"Acceleration Error":"7.7","MPJPE":"62.7","MPVPE":"74.4","PA-MPJPE":"40.6"},"uses_additional_data":false,"paper_date":"2023-11-16","paper":"/paper/temporal-aware-refinement-for-video-based","paper_url":"https://arxiv.org/abs/2311.09543v1","paper_title":"Temporal-Aware Refinement for Video-based Human Pose and Shape Recovery","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"Zolly (HRNet-w48)","metrics":{"MPJPE":"65","MPVPE":"76.3","PA-MPJPE":"39.8"},"uses_additional_data":false,"paper_date":"2023-03-24","paper":"/paper/zolly-zoom-focal-length-correctly-for","paper_url":"https://arxiv.org/abs/2303.13796v3","paper_title":"Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction","code":"https://github.com/wenjiawang0312/zolly","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"CycleAdapt (w/ 2D GT)","metrics":{"MPJPE":"64.7","MPVPE":"76.7","PA-MPJPE":"39.9"},"uses_additional_data":false,"paper_date":"2023-08-12","paper":"/paper/cyclic-test-time-adaptation-on-monocular","paper_url":"https://arxiv.org/abs/2308.06554v1","paper_title":"Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction","code":"https://github.com/hygenie1228/cycleadapt_release","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":6,"model":"PostoMETRO (HRNet-w48)","metrics":{"MPJPE":"67.7","MPVPE":"76.8","PA-MPJPE":"39.8"},"uses_additional_data":false,"paper_date":"2024-03-19","paper":"/paper/postometro-pose-token-enhanced-mesh","paper_url":"https://arxiv.org/abs/2403.12473v1","paper_title":"PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"CLIFF (3DPW+HumanWild+BEDLAM+AGORA)","metrics":{"MPJPE":"65.2","MPVPE":"76.8","PA-MPJPE":"41.9"},"uses_additional_data":false,"paper_date":"2024-03-17","paper":"/paper/3d-human-reconstruction-in-the-wild-with-1","paper_url":"https://arxiv.org/abs/2403.11111v2","paper_title":"3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"Hulk(ViT-L)","metrics":{"MPJPE":"66.3","MPVPE":"77.4","PA-MPJPE":"38.5"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/hulk-a-universal-knowledge-translator-for","paper_url":"https://arxiv.org/abs/2312.01697v4","paper_title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","code":"https://github.com/opengvlab/humanbench","n_code_links":2,"syntology":{"n_ran":13,"n_unverified":11,"n_samples":24,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"GenHMR","metrics":{"MPJPE":"68.1","MPVPE":"77.5","PA-MPJPE":"42.1"},"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":10,"model":"VirtualMarker","metrics":{"MPJPE":"67.5","MPVPE":"77.9","PA-MPJPE":"41.3"},"uses_additional_data":false,"paper_date":"2023-03-21","paper":"/paper/3d-human-mesh-estimation-from-virtual-markers-1","paper_url":"https://arxiv.org/abs/2303.11726v4","paper_title":"3D Human Mesh Estimation from Virtual Markers","code":"https://github.com/ShirleyMaxx/VirtualMarker","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":8,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"PostoMETRO (ResNet-50)","metrics":{"MPJPE":"68.4","MPVPE":"78.0","PA-MPJPE":"40.8"},"uses_additional_data":false,"paper_date":"2024-03-19","paper":"/paper/postometro-pose-token-enhanced-mesh","paper_url":"https://arxiv.org/abs/2403.12473v1","paper_title":"PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"SEFD_GT","metrics":{"MPJPE":"64.75","MPVPE":"78.36","PA-MPJPE":"43.79"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/sefd-learning-to-distill-complex-pose-and","paper_url":"http://openaccess.thecvf.com//content/ICCV2023/html/Yang_SEFD_Learning_to_Distill_Complex_Pose_and_Occlusion_ICCV_2023_paper.html","paper_title":"SEFD: Learning to Distill Complex Pose and Occlusion","code":"https://github.com/YangChangHee/ICCV2023_SEFD_RELEASE","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"PROM (CLIFF)","metrics":{"MPJPE":"67.6","MPVPE":"79.2","PA-MPJPE":"42.0"},"uses_additional_data":false,"paper_date":"2023-12-01","paper":"/paper/learning-unorthogonalized-matrices-for","paper_url":"https://arxiv.org/abs/2312.00462v1","paper_title":"Learning Unorthogonalized Matrices for Rotation Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"MotionBERT-HybrIK","metrics":{"MPJPE":"68.8","MPVPE":"79.4","PA-MPJPE":"40.6"},"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":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"MPT","metrics":{"MPJPE":"65.9","MPVPE":"79.4","PA-MPJPE":"42.8"},"uses_additional_data":false,"paper_date":"2022-11-24","paper":"/paper/mpt-mesh-pre-training-with-transformers-for","paper_url":"https://arxiv.org/abs/2211.13357v2","paper_title":"MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstruction","code":"https://github.com/pwc-1/Paper-9/tree/main/2/mpt","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"BioPose","metrics":{"MPJPE":"69.0","MPVPE":"79.8","PA-MPJPE":"39.5"},"uses_additional_data":false,"paper_date":"2025-01-14","paper":"/paper/biopose-biomechanically-accurate-3d-pose","paper_url":"https://arxiv.org/abs/2501.07800v1","paper_title":"BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"Hulk(ViT-B)","metrics":{"MPJPE":"67","MPVPE":"79.8","PA-MPJPE":"39.9"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/hulk-a-universal-knowledge-translator-for","paper_url":"https://arxiv.org/abs/2312.01697v4","paper_title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","code":"https://github.com/opengvlab/humanbench","n_code_links":2,"syntology":{"n_ran":13,"n_unverified":11,"n_samples":24,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"BoPR (HR-W48)","metrics":{"MPJPE":"65.4","MPVPE":"80.8","PA-MPJPE":"42.5"},"uses_additional_data":false,"paper_date":"2023-03-21","paper":"/paper/bopr-body-aware-part-regressor-for-human","paper_url":"https://arxiv.org/abs/2303.11675v2","paper_title":"BoPR: Body-aware Part Regressor for Human Shape and Pose Estimation","code":"https://github.com/cyk990422/bopr","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"ARTS (Resnet50 L=16)","metrics":{"Acceleration Error":"6.5","MPJPE":"67.7","MPVPE":"81.4","PA-MPJPE":"46.5"},"uses_additional_data":false,"paper_date":"2024-10-21","paper":"/paper/arts-semi-analytical-regressor-using","paper_url":"https://arxiv.org/abs/2410.15582v1","paper_title":"ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos","code":"https://github.com/securade/hub","n_code_links":2,"syntology":null},{"rank_in_archive_order":20,"model":"RemoCap","metrics":{"MPJPE":"72.7","MPVPE":"81.9","PA-MPJPE":"44.1"},"uses_additional_data":false,"paper_date":"2024-05-21","paper":"/paper/remocap-disentangled-representation-learning","paper_url":"https://arxiv.org/abs/2405.12724v1","paper_title":"RemoCap: Disentangled Representation Learning for Motion Capture","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"DynaBOA (w/ 2D GT)","metrics":{"MPJPE":"65.5","MPVPE":"82","PA-MPJPE":"40.4"},"uses_additional_data":false,"paper_date":"2021-11-07","paper":"/paper/out-of-domain-human-mesh-reconstruction-via","paper_url":"https://arxiv.org/abs/2111.04017v1","paper_title":"Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation","code":"https://github.com/syguan96/dynaboa","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"SMPLer-L","metrics":{"MPJPE":"73.7","MPVPE":"82","PA-MPJPE":"43.4"},"uses_additional_data":false,"paper_date":"2024-04-23","paper":"/paper/smpler-taming-transformers-for-monocular-3d","paper_url":"https://arxiv.org/abs/2404.15276v1","paper_title":"SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation","code":"https://github.com/xuxy09/smpler","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"HMR 2.0","metrics":{"MPJPE":"69.8","MPVPE":"82.2","PA-MPJPE":"44.4"},"uses_additional_data":false,"paper_date":"2023-05-31","paper":"/paper/humans-in-4d-reconstructing-and-tracking","paper_url":"https://arxiv.org/abs/2305.20091v3","paper_title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","code":"https://github.com/shubham-goel/4D-Humans","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"HybrIK (HRNet-W48)","metrics":{"MPJPE":"71.6","MPVPE":"82.3","PA-MPJPE":"41.8"},"uses_additional_data":false,"paper_date":"2023-04-12","paper":"/paper/hybrik-x-hybrid-analytical-neural-inverse","paper_url":"https://arxiv.org/abs/2304.05690v1","paper_title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","code":"https://github.com/jeffffffli/HybrIK","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"DeFormer","metrics":{"MPJPE":"72.9","MPVPE":"82.6","PA-MPJPE":"44.3"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/deformable-mesh-transformer-for-3d-human-mesh","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Yoshiyasu_Deformable_Mesh_Transformer_for_3D_Human_Mesh_Recovery_CVPR_2023_paper.html","paper_title":"Deformable Mesh Transformer for 3D Human Mesh Recovery","code":"https://github.com/yusukey03012/deformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"HybrIK-Transformer (HrNet-48)","metrics":{"MPJPE":"71.6","MPVPE":"83.6","PA-MPJPE":"42.3"},"uses_additional_data":false,"paper_date":"2023-02-09","paper":"/paper/hybrik-transformer","paper_url":"https://arxiv.org/abs/2302.04774v4","paper_title":"3D Human Pose and Shape Estimation via HybrIK-Transformer","code":"https://github.com/boreshkinai/hybrik-transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"PSVT","metrics":{"MPJPE":"73.1","MPVPE":"84","PA-MPJPE":"43.5"},"uses_additional_data":false,"paper_date":"2023-03-16","paper":"/paper/psvt-end-to-end-multi-person-3d-pose-and","paper_url":"https://arxiv.org/abs/2303.09187v1","paper_title":"PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"IKOL","metrics":{"MPJPE":"71.1","MPVPE":"84.1","PA-MPJPE":"44.5"},"uses_additional_data":false,"paper_date":"2023-02-02","paper":"/paper/ikol-inverse-kinematics-optimization-layer","paper_url":"https://arxiv.org/abs/2302.01058v2","paper_title":"IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation","code":"https://github.com/juzezhang/ikol","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"TokenHMR (SD + ITW + BL)","metrics":{"MPJPE":"71","MPVPE":"84.6","PA-MPJPE":"44.3"},"uses_additional_data":false,"paper_date":"2024-04-25","paper":"/paper/tokenhmr-advancing-human-mesh-recovery-with-a","paper_url":"https://arxiv.org/abs/2404.16752v1","paper_title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","code":"https://github.com/saidwivedi/TokenHMR","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"HybrIK","metrics":{"MPJPE":"74.1","MPVPE":"86.5","PA-MPJPE":"45.0"},"uses_additional_data":false,"paper_date":"2020-11-30","paper":"/paper/hybrik-a-hybrid-analytical-neural-inverse","paper_url":"https://arxiv.org/abs/2011.14672v4","paper_title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","code":"https://github.com/jeffffffli/HybrIK","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"NIKI (Twist-and-Swing)","metrics":{"MPJPE":"71.3","MPVPE":"86.6","PA-MPJPE":"40.6"},"uses_additional_data":false,"paper_date":"2023-05-15","paper":"/paper/niki-neural-inverse-kinematics-with","paper_url":"https://arxiv.org/abs/2305.08590v1","paper_title":"NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation","code":"https://github.com/jeff-sjtu/niki","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":32,"model":"HeatER","metrics":{"MPJPE":"73.4","MPVPE":"86.9","PA-MPJPE":"45.9"},"uses_additional_data":false,"paper_date":"2022-05-30","paper":"/paper/heater-an-efficient-and-unified-network-for","paper_url":"https://arxiv.org/abs/2205.15448v3","paper_title":"FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER","code":"https://github.com/zczcwh/feater","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"ImpHMR","metrics":{"MPJPE":"74.3","MPVPE":"87.1","PA-MPJPE":"45.4"},"uses_additional_data":false,"paper_date":"2023-06-30","paper":"/paper/implicit-3d-human-mesh-recovery-using-1","paper_url":"https://arxiv.org/abs/2306.17651v2","paper_title":"Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"XFormer (HRNet)","metrics":{"MPJPE":"75","MPVPE":"87.1","PA-MPJPE":"45.7"},"uses_additional_data":false,"paper_date":"2023-05-18","paper":"/paper/xformer-fast-and-accurate-monocular-3d-body","paper_url":"https://arxiv.org/abs/2305.11101v1","paper_title":"XFormer: Fast and Accurate Monocular 3D Body Capture","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"POTTER","metrics":{"MPJPE":"75","MPVPE":"87.4","PA-MPJPE":"44.8"},"uses_additional_data":false,"paper_date":"2023-03-23","paper":"/paper/potter-pooling-attention-transformer-for","paper_url":"https://arxiv.org/abs/2303.13357v1","paper_title":"POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery","code":"https://github.com/zczcwh/potter","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"INT-2 (ResNet-50)","metrics":{"Acceleration Error":"16.5","MPJPE":"75.6","MPVPE":"87.9","PA-MPJPE":"42"},"uses_additional_data":false,"paper_date":"2023-03-01","paper":"/paper/capturing-the-motion-of-every-joint-3d-human","paper_url":"https://arxiv.org/abs/2303.00298v1","paper_title":"Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens","code":"https://github.com/yangsenius/int_hmr_model","n_code_links":1,"syntology":null},{"rank_in_archive_order":37,"model":"MotionBERT (Finetune)","metrics":{"MPJPE":"76.9","MPVPE":"88.1","PA-MPJPE":"47.2"},"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":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"BOA (w/ 2D GT)","metrics":{"MPJPE":"77.2","MPVPE":"91.2","PA-MPJPE":"49.5"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/bilevel-online-adaptation-for-out-of-domain","paper_url":"https://arxiv.org/abs/2103.16449v1","paper_title":"Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction","code":"https://github.com/syguan96/BOA","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"SEFD","metrics":{"MPJPE":"77.37","MPVPE":"92.60","PA-MPJPE":"49.39"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/sefd-learning-to-distill-complex-pose-and","paper_url":"http://openaccess.thecvf.com//content/ICCV2023/html/Yang_SEFD_Learning_to_Distill_Complex_Pose_and_Occlusion_ICCV_2023_paper.html","paper_title":"SEFD: Learning to Distill Complex Pose and Occlusion","code":"https://github.com/YangChangHee/ICCV2023_SEFD_RELEASE","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"DST-VIBE","metrics":{"Acceleration Error":"11","MPJPE":"76.7","MPVPE":"93.5","PA-MPJPE":"50.3"},"uses_additional_data":false,"paper_date":"2021-10-22","paper":"/paper/deep-two-stream-video-inference-for-human","paper_url":"https://arxiv.org/abs/2110.11680v1","paper_title":"Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":41,"model":"LMR","metrics":{"Acceleration Error":"15.6","MPJPE":"81.7","MPVPE":"93.6","PA-MPJPE":"51.2"},"uses_additional_data":false,"paper_date":"2021-07-27","paper":"/paper/learning-local-recurrent-models-for-human","paper_url":"https://arxiv.org/abs/2107.12847v1","paper_title":"Learning Local Recurrent Models for Human Mesh Recovery","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":42,"model":"GLoT","metrics":{"Acceleration Error":"6.6","MPJPE":"80.7","MPVPE":"96.3","PA-MPJPE":"50.6"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/global-to-local-modeling-for-video-based-3d","paper_url":"https://arxiv.org/abs/2303.14747v1","paper_title":"Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation","code":"https://github.com/sxl142/glot","n_code_links":1,"syntology":null},{"rank_in_archive_order":43,"model":"KAMA","metrics":{"MPVPE":"97.0","PA-MPJPE":"51.1"},"uses_additional_data":false,"paper_date":"2021-04-27","paper":"/paper/kama-3d-keypoint-aware-body-mesh-articulation","paper_url":"https://arxiv.org/abs/2104.13502v1","paper_title":"KAMA: 3D Keypoint Aware Body Mesh Articulation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":44,"model":"TRACE","metrics":{"MPJPE":"79.1","MPVPE":"97.3","PA-MPJPE":"37.8"},"uses_additional_data":false,"paper_date":"2023-06-05","paper":"/paper/trace-5d-temporal-regression-of-avatars-with-1","paper_url":"https://arxiv.org/abs/2306.02850v2","paper_title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","code":"https://github.com/Arthur151/ROMP","n_code_links":3,"syntology":{"n_ran":5,"n_unverified":15,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":45,"model":"TAPE (T=16)","metrics":{"Acceleration Error":"8.9","MPJPE":"79.9","MPVPE":"98.1","PA-MPJPE":"51.5"},"uses_additional_data":false,"paper_date":"2023-04-29","paper":"/paper/tape-temporal-attention-based-probabilistic","paper_url":"https://arxiv.org/abs/2305.00181v1","paper_title":"TAPE: Temporal Attention-based Probabilistic human pose and shape Estimation","code":"https://github.com/nikosvasilik/tape","n_code_links":1,"syntology":null},{"rank_in_archive_order":46,"model":"VIBE","metrics":{"Acceleration Error":"23.4","MPJPE":"82.9","MPVPE":"99.1","Number of parameters (M)":"72.43","PA-MPJPE":"51.9"},"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":47,"model":"MPS-Net (T=16)","metrics":{"Acceleration Error":"7.4","FLOPs (G)":"4.45","MPJPE":"84.3","MPVPE":"99.7","Number of parameters (M)":"39.63","PA-MPJPE":"52.1"},"uses_additional_data":false,"paper_date":"2022-03-16","paper":"/paper/capturing-humans-in-motion-temporal-attentive","paper_url":"https://arxiv.org/abs/2203.08534v1","paper_title":"Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":48,"model":"CycleAdapt (w/o 2D GT)","metrics":{"MPJPE":"84.4","MPVPE":"99.9","PA-MPJPE":"51.1"},"uses_additional_data":false,"paper_date":"2023-08-12","paper":"/paper/cyclic-test-time-adaptation-on-monocular","paper_url":"https://arxiv.org/abs/2308.06554v1","paper_title":"Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction","code":"https://github.com/hygenie1228/cycleadapt_release","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":49,"model":"TePose (T=6)","metrics":{"Acceleration Error":"11.4","MPJPE":"84.6","MPVPE":"100.3","PA-MPJPE":"52.3"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/live-stream-temporally-embedded-3d-human-body","paper_url":"https://arxiv.org/abs/2207.12537v1","paper_title":"Live Stream Temporally Embedded 3D Human Body Pose and Shape Estimation","code":"https://github.com/ostadabbas/tepose","n_code_links":1,"syntology":null},{"rank_in_archive_order":50,"model":"Self-Attentive","metrics":{"Acceleration Error":"77.9","MPJPE":"85.8","MPVPE":"100.6","PA-MPJPE":"50.4"},"uses_additional_data":false,"paper_date":"2021-03-26","paper":"/paper/self-attentive-3d-human-pose-and-shape","paper_url":"https://arxiv.org/abs/2103.14182v2","paper_title":"Self-Attentive 3D Human Pose and Shape Estimation from Videos","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":51,"model":"STR","metrics":{"Acceleration Error":"6.9","MPJPE":"85.2","MPVPE":"101.2","PA-MPJPE":"52.4"},"uses_additional_data":false,"paper_date":"2022-10-07","paper":"/paper/spatio-temporal-tendency-reasoning-for-human","paper_url":"https://arxiv.org/abs/2210.03659v2","paper_title":"Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videos","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":52,"model":"DDT","metrics":{"Acceleration Error":"6.6","MPJPE":"85.9","MPVPE":"101.2","PA-MPJPE":"53.3"},"uses_additional_data":false,"paper_date":"2023-03-23","paper":"/paper/ddt-a-diffusion-driven-transformer-based","paper_url":"https://arxiv.org/abs/2303.13397v6","paper_title":"DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":53,"model":"CLIFF","metrics":{"MPJPE":"87.3","MPVPE":"102.1","PA-MPJPE":"52.7"},"uses_additional_data":false,"paper_date":"2024-03-17","paper":"/paper/3d-human-reconstruction-in-the-wild-with-1","paper_url":"https://arxiv.org/abs/2403.11111v2","paper_title":"3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":54,"model":"TCMR (T=16 w/o H3.6M)","metrics":{"Acceleration Error":"7.1","MPJPE":"86.5","MPVPE":"102.9","PA-MPJPE":"52.7"},"uses_additional_data":false,"paper_date":"2020-11-17","paper":"/paper/beyond-static-features-for-temporally","paper_url":"https://arxiv.org/abs/2011.08627v4","paper_title":"Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video","code":"https://github.com/hongsukchoi/TCMR_RELEASE","n_code_links":1,"syntology":null},{"rank_in_archive_order":55,"model":"MoCap-SPIN + PoseBERT","metrics":{"Acceleration Error":"8.3","MPJPE":"89.4","MPVPE":"103.8","PA-MPJPE":"52.9"},"uses_additional_data":false,"paper_date":"2021-10-18","paper":"/paper/leveraging-mocap-data-for-human-mesh-recovery","paper_url":"https://arxiv.org/abs/2110.09243v1","paper_title":"Leveraging MoCap Data for Human Mesh Recovery","code":"https://github.com/naver/posebert","n_code_links":1,"syntology":null},{"rank_in_archive_order":56,"model":"GTRS","metrics":{"MPJPE":"88.5","MPVPE":"106.2","PA-MPJPE":"58.9"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/a-lightweight-graph-transformer-network-for","paper_url":"https://arxiv.org/abs/2111.12696v3","paper_title":"A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose","code":"https://github.com/zczcwh/gtrs","n_code_links":1,"syntology":null},{"rank_in_archive_order":57,"model":"MUG","metrics":{"MPJPE":"87","MPVPE":"106.2","PA-MPJPE":"60.5"},"uses_additional_data":false,"paper_date":"2022-05-25","paper":"/paper/mug-multi-human-graph-network-for-3d-mesh","paper_url":"https://arxiv.org/abs/2205.12583v3","paper_title":"MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":58,"model":"3DCrowdNet","metrics":{"MPJPE":"85.8","MPVPE":"108.5","PA-MPJPE":"55.8"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/3dcrowdnet-2d-human-pose-guided3d-crowd-human","paper_url":"https://arxiv.org/abs/2104.07300v3","paper_title":"Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes","code":"https://github.com/hongsukchoi/3dcrowdnet_release","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":59,"model":"PC-HMR","metrics":{"MPJPE":"87.8","MPVPE":"108.6","PA-MPJPE":"66.9"},"uses_additional_data":false,"paper_date":"2021-03-16","paper":"/paper/pc-hmr-pose-calibration-for-3d-human-mesh","paper_url":"https://arxiv.org/abs/2103.09009v2","paper_title":"PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":60,"model":"CHOMP","metrics":{"MPJPE":"83.7","MPVPE":"110.1","PA-MPJPE":"51.7"},"uses_additional_data":false,"paper_date":"2022-07-12","paper":"/paper/occluded-human-body-capture-with-self","paper_url":"https://arxiv.org/abs/2207.05375v1","paper_title":"Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior","code":"https://github.com/boycehbz/chomp","n_code_links":1,"syntology":null},{"rank_in_archive_order":61,"model":"TCMR (T=16 w/o 3DPW)","metrics":{"Acceleration Error":"7","MPJPE":"95","MPVPE":"111.5","PA-MPJPE":"55.8"},"uses_additional_data":false,"paper_date":"2020-11-17","paper":"/paper/beyond-static-features-for-temporally","paper_url":"https://arxiv.org/abs/2011.08627v4","paper_title":"Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video","code":"https://github.com/hongsukchoi/TCMR_RELEASE","n_code_links":1,"syntology":null},{"rank_in_archive_order":62,"model":"Wenshuo et a;.","metrics":{"Acceleration Error":"17.1","MPJPE":"89.4","MPVPE":"112.6","PA-MPJPE":"51.4"},"uses_additional_data":false,"paper_date":"2023-05-30","paper":"/paper/decomposed-human-motion-prior-for-video-pose","paper_url":"https://arxiv.org/abs/2305.18743v3","paper_title":"Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":63,"model":"SPIN","metrics":{"MPJPE":"96.9","MPVPE":"116.4","PA-MPJPE":"59.2"},"uses_additional_data":false,"paper_date":"2019-09-27","paper":"/paper/learning-to-reconstruct-3d-human-pose-and","paper_url":"https://arxiv.org/abs/1909.12828v1","paper_title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","code":"https://github.com/nkolot/SPIN","n_code_links":1,"syntology":null},{"rank_in_archive_order":64,"model":"BMP","metrics":{"MPJPE":"104.1","MPVPE":"119.3","PA-MPJPE":"63.8"},"uses_additional_data":false,"paper_date":"2021-05-06","paper":"/paper/body-meshes-as-points","paper_url":"https://arxiv.org/abs/2105.02467v2","paper_title":"Body Meshes as Points","code":"https://github.com/jfzhang95/BMP","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":65,"model":"ZeDO (S=1,J=17)","metrics":{"MPJPE":"69.7","PA-MPJPE":"40.3"},"uses_additional_data":false,"paper_date":"2023-07-07","paper":"/paper/back-to-optimization-diffusion-based-zero","paper_url":"https://arxiv.org/abs/2307.03833v3","paper_title":"Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation","code":"https://github.com/ipl-uw/ZeDO-Release","n_code_links":1,"syntology":null},{"rank_in_archive_order":66,"model":"3DHR-Co (w/ 2D GT)","metrics":{"MPJPE":"63.72","PA-MPJPE":"42.11"},"uses_additional_data":false,"paper_date":"2023-10-02","paper":"/paper/3dhr-co-a-collaborative-test-time-refinement","paper_url":"https://arxiv.org/abs/2310.01291v1","paper_title":"3DHR-Co: A Collaborative Test-time Refinement Framework for In-the-Wild 3D Human-Body Reconstruction Task","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":67,"model":"ZeDO (Cross Dataset)","metrics":{"MPJPE":"80.9","PA-MPJPE":"42.6"},"uses_additional_data":false,"paper_date":"2023-07-07","paper":"/paper/back-to-optimization-diffusion-based-zero","paper_url":"https://arxiv.org/abs/2307.03833v3","paper_title":"Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation","code":"https://github.com/ipl-uw/ZeDO-Release","n_code_links":1,"syntology":null},{"rank_in_archive_order":68,"model":"OSX","metrics":{"MPJPE":"74.7","PA-MPJPE":"45.1"},"uses_additional_data":false,"paper_date":"2023-03-28","paper":"/paper/one-stage-3d-whole-body-mesh-recovery-with","paper_url":"https://arxiv.org/abs/2303.16160v1","paper_title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","code":"https://github.com/IDEA-Research/OSX","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":69,"model":"IVT (f=5)","metrics":{"PA-MPJPE":"46"},"uses_additional_data":false,"paper_date":"2022-08-06","paper":"/paper/ivt-an-end-to-end-instance-guided-video","paper_url":"https://arxiv.org/abs/2208.03431v1","paper_title":"IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":70,"model":"DeciWatch-PARE","metrics":{"MPJPE":"75.5","PA-MPJPE":"46.4"},"uses_additional_data":false,"paper_date":"2022-03-16","paper":"/paper/deciwatch-a-simple-baseline-for-10x-efficient","paper_url":"https://arxiv.org/abs/2203.08713v2","paper_title":"DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation","code":"https://github.com/cure-lab/DeciWatch","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":71,"model":"TCFormer","metrics":{"MPJPE":"80.6","PA-MPJPE":"49.3"},"uses_additional_data":false,"paper_date":"2022-04-19","paper":"/paper/not-all-tokens-are-equal-human-centric-visual","paper_url":"https://arxiv.org/abs/2204.08680v3","paper_title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","code":"https://github.com/zengwang430521/tcformer","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":72,"model":"MeTRAbs","metrics":{"MPJPE":"68.8","PA-MPJPE":"49.7"},"uses_additional_data":false,"paper_date":"2020-07-12","paper":"/paper/metrabs-metric-scale-truncation-robust","paper_url":"https://arxiv.org/abs/2007.07227v2","paper_title":"MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation","code":"https://github.com/isarandi/metrabs","n_code_links":1,"syntology":null},{"rank_in_archive_order":73,"model":"FS+WS+OPT(KA+BA+S, 16 frames)","metrics":{"MPJPE":"80.2","PA-MPJPE":"49.8"},"uses_additional_data":false,"paper_date":"2020-03-23","paper":"/paper/weakly-supervised-3d-human-pose-and-shape","paper_url":"https://arxiv.org/abs/2003.10350v2","paper_title":"Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":74,"model":"THUNDR","metrics":{"MPJPE":"74.8","PA-MPJPE":"51.5"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/thundr-transformer-based-3d-human","paper_url":"https://arxiv.org/abs/2106.09336v1","paper_title":"THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":75,"model":"EFT","metrics":{"PA-MPJPE":"51.6"},"uses_additional_data":false,"paper_date":"2020-04-07","paper":"/paper/exemplar-fine-tuning-for-3d-human-pose","paper_url":"https://arxiv.org/abs/2004.03686v3","paper_title":"Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation","code":"https://github.com/facebookresearch/eft","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":76,"model":"UniHPE (GT)","metrics":{"PA-MPJPE":"51.6"},"uses_additional_data":false,"paper_date":"2023-11-24","paper":"/paper/unihpe-towards-unified-human-pose-estimation","paper_url":"https://arxiv.org/abs/2311.16477v1","paper_title":"UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":77,"model":"MION","metrics":{"MPJPE":"81.98","PA-MPJPE":"52.34"},"uses_additional_data":false,"paper_date":"2021-12-24","paper":"/paper/multi-initialization-optimization-network-for","paper_url":"https://arxiv.org/abs/2112.12917v1","paper_title":"Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":78,"model":"SPEC","metrics":{"PA-MPJPE":"53.2"},"uses_additional_data":false,"paper_date":"2021-10-01","paper":"/paper/spec-seeing-people-in-the-wild-with-an","paper_url":"https://arxiv.org/abs/2110.00620v2","paper_title":"SPEC: Seeing People in the Wild with an Estimated Camera","code":"https://github.com/mkocabas/SPEC","n_code_links":1,"syntology":null},{"rank_in_archive_order":79,"model":"HuManiFlow","metrics":{"MPJPE":"83.9","PA-MPJPE":"53.4"},"uses_additional_data":false,"paper_date":"2023-05-11","paper":"/paper/humaniflow-ancestor-conditioned-normalising","paper_url":"https://arxiv.org/abs/2305.06968v1","paper_title":"HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation","code":"https://github.com/akashsengupta1997/humaniflow","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":80,"model":"Hierarchical Probabilistic Humans","metrics":{"MPJPE":"84.9","PA-MPJPE":"53.6"},"uses_additional_data":false,"paper_date":"2021-10-03","paper":"/paper/hierarchical-kinematic-probability","paper_url":"https://arxiv.org/abs/2110.00990v2","paper_title":"Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild","code":"https://github.com/akashsengupta1997/hierarchicalprobabilistic3dhuman","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":81,"model":"BlanketGen","metrics":{"PA-MPJPE":"53.96"},"uses_additional_data":false,"paper_date":"2022-10-21","paper":"/paper/blanketgen-a-synthetic-blanket-occlusion","paper_url":"https://arxiv.org/abs/2210.12035v2","paper_title":"BlanketGen - A synthetic blanket occlusion augmentation pipeline for MoCap datasets","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":82,"model":"Hand4Whole","metrics":{"PA-MPJPE":"54.4"},"uses_additional_data":false,"paper_date":"2020-11-23","paper":"/paper/pose2pose-3d-positional-pose-guided-3d","paper_url":"https://arxiv.org/abs/2011.11534v4","paper_title":"Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation","code":"https://github.com/mks0601/Hand4Whole_RELEASE","n_code_links":1,"syntology":null},{"rank_in_archive_order":83,"model":"DaNet-DensePose2SMPL","metrics":{"MPJPE":"85.5","PA-MPJPE":"54.8"},"uses_additional_data":false,"paper_date":"2019-12-31","paper":"/paper/learning-3d-human-shape-and-pose-from-dense","paper_url":"https://arxiv.org/abs/1912.13344v2","paper_title":"Learning 3D Human Shape and Pose from Dense Body Parts","code":"https://github.com/HongwenZhang/DaNet-DensePose2SMPL","n_code_links":1,"syntology":null},{"rank_in_archive_order":84,"model":"ProHMR + fitting","metrics":{"PA-MPJPE":"55.1"},"uses_additional_data":false,"paper_date":"2021-08-26","paper":"/paper/probabilistic-modeling-for-human-mesh","paper_url":"https://arxiv.org/abs/2108.11944v1","paper_title":"Probabilistic Modeling for Human Mesh Recovery","code":"https://github.com/nkolot/ProHMR","n_code_links":1,"syntology":null},{"rank_in_archive_order":85,"model":"TUCH","metrics":{"MPJPE":" 84.9","PA-MPJPE":"55.5"},"uses_additional_data":false,"paper_date":"2021-04-07","paper":"/paper/on-self-contact-and-human-pose","paper_url":"https://arxiv.org/abs/2104.03176v2","paper_title":"On Self-Contact and Human Pose","code":"https://github.com/muelea/tuch","n_code_links":1,"syntology":null},{"rank_in_archive_order":86,"model":"HUND (FS+SS)","metrics":{"MPJPE":"81.4","PA-MPJPE":"57.5"},"uses_additional_data":false,"paper_date":"2020-08-16","paper":"/paper/neural-descent-for-visual-3d-human-pose-and","paper_url":"https://arxiv.org/abs/2008.06910v2","paper_title":"Neural Descent for Visual 3D Human Pose and Shape","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":87,"model":"LASOR","metrics":{"PA-MPJPE":"57.9"},"uses_additional_data":false,"paper_date":"2021-08-01","paper":"/paper/lasor-learning-accurate-3d-human-pose-and","paper_url":"https://arxiv.org/abs/2108.00351v5","paper_title":"LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering","code":"https://github.com/iGame-Lab/LASOR","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":88,"model":"RSC-Net","metrics":{"MPJPE":"96.36","PA-MPJPE":"58.98"},"uses_additional_data":false,"paper_date":"2020-07-27","paper":"/paper/3d-human-shape-and-pose-from-a-single-low","paper_url":"https://arxiv.org/abs/2007.13666v2","paper_title":"3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning","code":"https://github.com/xuxy09/texformer","n_code_links":2,"syntology":null},{"rank_in_archive_order":89,"model":"BeyondWeak","metrics":{"MPJPE":"83.2","PA-MPJPE":"59.7"},"uses_additional_data":false,"paper_date":"2020-09-14","paper":"/paper/beyond-weak-perspective-for-monocular-3d","paper_url":"https://arxiv.org/abs/2009.06549v1","paper_title":"Beyond Weak Perspective for Monocular 3D Human Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":90,"model":"THUNDR (WS)","metrics":{"MPJPE":"86.8","PA-MPJPE":"59.9"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/thundr-transformer-based-3d-human","paper_url":"https://arxiv.org/abs/2106.09336v1","paper_title":"THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":91,"model":"Biggs [3]","metrics":{"PA-MPJPE":"59.9"},"uses_additional_data":false,"paper_date":"2021-08-26","paper":"/paper/probabilistic-modeling-for-human-mesh","paper_url":"https://arxiv.org/abs/2108.11944v1","paper_title":"Probabilistic Modeling for Human Mesh Recovery","code":"https://github.com/nkolot/ProHMR","n_code_links":1,"syntology":null},{"rank_in_archive_order":92,"model":"FrankMocap","metrics":{"MPJPE":"94.3","PA-MPJPE":"60"},"uses_additional_data":false,"paper_date":"2021-08-13","paper":"/paper/frankmocap-a-monocular-3d-whole-body-pose","paper_url":"https://arxiv.org/abs/2108.06428v1","paper_title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","code":"https://github.com/facebookresearch/frankmocap","n_code_links":1,"syntology":null},{"rank_in_archive_order":93,"model":"ExPose","metrics":{"MPJPE":"93.4","PA-MPJPE":"60.7"},"uses_additional_data":false,"paper_date":"2020-08-20","paper":"/paper/monocular-expressive-body-regression-through","paper_url":"https://arxiv.org/abs/2008.09062v1","paper_title":"Monocular Expressive Body Regression through Body-Driven Attention","code":"https://github.com/vchoutas/expose","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":94,"model":"Prob3DHumans","metrics":{"MPJPE":"90.9","PA-MPJPE":"61"},"uses_additional_data":false,"paper_date":"2021-03-19","paper":"/paper/probabilistic-3d-human-shape-and-pose","paper_url":"https://arxiv.org/abs/2103.10978v2","paper_title":"Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":95,"model":"Dual network","metrics":{"PA-MPJPE":"61.7"},"uses_additional_data":false,"paper_date":"2022-05-02","paper":"/paper/dual-networks-based-3d-multi-person-pose","paper_url":"https://arxiv.org/abs/2205.00748v3","paper_title":"Dual networks based 3D Multi-Person Pose Estimation from Monocular Video","code":"https://github.com/3dpose/3D-Multi-Person-Pose","n_code_links":1,"syntology":null},{"rank_in_archive_order":96,"model":"SHAPY (SMPL-X)","metrics":{"MPJPE":"95.2","PA-MPJPE":"62.6"},"uses_additional_data":false,"paper_date":"2022-06-14","paper":"/paper/accurate-3d-body-shape-regression-using-1","paper_url":"https://arxiv.org/abs/2206.07036v1","paper_title":"Accurate 3D Body Shape Regression using Metric and Semantic Attributes","code":"https://github.com/muelea/shapy","n_code_links":1,"syntology":null},{"rank_in_archive_order":97,"model":"PoseNet3D","metrics":{"PA-MPJPE":"63.2"},"uses_additional_data":false,"paper_date":"2020-03-07","paper":"/paper/posenet3d-unsupervised-3d-human-shape-and","paper_url":"https://arxiv.org/abs/2003.03473v2","paper_title":"PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillation","code":"https://github.com/dizhongzhu/Humanbody_Literatures","n_code_links":1,"syntology":null},{"rank_in_archive_order":98,"model":"GnTCN","metrics":{"PA-MPJPE":"64.2"},"uses_additional_data":false,"paper_date":"2020-12-22","paper":"/paper/graph-and-temporal-convolutional-networks-for","paper_url":"https://arxiv.org/abs/2012.11806v3","paper_title":"Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos","code":"https://github.com/3dpose/GnTCN","n_code_links":1,"syntology":null},{"rank_in_archive_order":99,"model":"ProHMR","metrics":{"PA-MPJPE":"65"},"uses_additional_data":false,"paper_date":"2021-08-26","paper":"/paper/probabilistic-modeling-for-human-mesh","paper_url":"https://arxiv.org/abs/2108.11944v1","paper_title":"Probabilistic Modeling for Human Mesh Recovery","code":"https://github.com/nkolot/ProHMR","n_code_links":1,"syntology":null},{"rank_in_archive_order":100,"model":"UniHPE-w48","metrics":{"PA-MPJPE":"65.7"},"uses_additional_data":false,"paper_date":"2023-11-24","paper":"/paper/unihpe-towards-unified-human-pose-estimation","paper_url":"https://arxiv.org/abs/2311.16477v1","paper_title":"UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":101,"model":"HW-HuP","metrics":{"PA-MPJPE":"66.1"},"uses_additional_data":false,"paper_date":"2021-05-23","paper":"/paper/heuristic-weakly-supervised-3d-human-pose","paper_url":"https://arxiv.org/abs/2105.10996v3","paper_title":"Heuristic Weakly Supervised 3D Human Pose Estimation","code":"https://github.com/ostadabbas/hw-hup","n_code_links":2,"syntology":null},{"rank_in_archive_order":102,"model":"STRAPS","metrics":{"PA-MPJPE":"66.8"},"uses_additional_data":false,"paper_date":"2020-09-21","paper":"/paper/synthetic-training-for-accurate-3d-human-pose","paper_url":"https://arxiv.org/abs/2009.10013v2","paper_title":"Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild","code":"https://github.com/akashsengupta1997/STRAPS-3DHumanShapePose","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":103,"model":"PoseTriplet","metrics":{"MPJPE":"115","PA-MPJPE":"69.5"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/posetriplet-co-evolving-3d-human-pose","paper_url":"https://arxiv.org/abs/2203.15625v1","paper_title":"PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision","code":"https://github.com/garfield-kh/posetriplet","n_code_links":1,"syntology":null},{"rank_in_archive_order":104,"model":"Spatio-Temporal Network (T=128)","metrics":{"PA-MPJPE":"71.8"},"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":105,"model":"Non-Local Latent Relation Distillation","metrics":{"PA-MPJPE":"72.1"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/non-local-latent-relation-distillation-for-1","paper_url":"https://arxiv.org/abs/2204.01971v2","paper_title":"Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":106,"model":"HMMR (T=20)","metrics":{"Acceleration Error":"15.2","MPJPE":"116.5","PA-MPJPE":"72.6"},"uses_additional_data":false,"paper_date":"2018-12-04","paper":"/paper/learning-3d-human-dynamics-from-video","paper_url":"https://arxiv.org/abs/1812.01601v4","paper_title":"Learning 3D Human Dynamics from Video","code":"https://github.com/akanazawa/human_dynamics","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":107,"model":"HR-Net+ST-GCN+PoseAug","metrics":{"PA-MPJPE":"73.2"},"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":108,"model":"ISO","metrics":{"PA-MPJPE":"75.8"},"uses_additional_data":false,"paper_date":"2020-07-04","paper":"/paper/inference-stage-optimization-for-cross","paper_url":"https://arxiv.org/abs/2007.02054v1","paper_title":"Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":109,"model":"PONet","metrics":{"PA-MPJPE":"76.2"},"uses_additional_data":false,"paper_date":"2021-12-21","paper":"/paper/ponet-robust-3d-human-pose-estimation-via","paper_url":"https://arxiv.org/abs/2112.11153v1","paper_title":"PONet: Robust 3D Human Pose Estimation via Learning Orientations Only","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":110,"model":"MVM","metrics":{"PA-MPJPE":"78.2"},"uses_additional_data":false,"paper_date":"2020-04-11","paper":"/paper/multi-view-matching-mvm-facilitating-multi","paper_url":"https://arxiv.org/abs/2004.05275v1","paper_title":"Multi-View Matching (MVM): Facilitating Multi-Person 3D Pose Estimation Learning with Action-Frozen People Video","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":111,"model":"TP-Net","metrics":{"PA-MPJPE":"92.2"},"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":112,"model":"SMPLify","metrics":{"PA-MPJPE":"106.8"},"uses_additional_data":false,"paper_date":"2016-07-27","paper":"/paper/keep-it-smpl-automatic-estimation-of-3d-human","paper_url":"http://arxiv.org/abs/1607.08128v1","paper_title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","code":"https://github.com/Jtoo/fitting_human_smpl_model","n_code_links":2,"syntology":null},{"rank_in_archive_order":113,"model":"Simple-baseline","metrics":{"PA-MPJPE":"157.0"},"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":114,"model":"HybridCap","metrics":{"MPJPE":"72.1"},"uses_additional_data":false,"paper_date":"2022-03-17","paper":"/paper/hybridcap-inertia-aid-monocular-capture-of","paper_url":"https://arxiv.org/abs/2203.09287v2","paper_title":"HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":115,"model":"PARE + HANet (T=51)","metrics":{"Acceleration Error":"8","MPJPE":"74.6"},"uses_additional_data":false,"paper_date":"2022-11-29","paper":"/paper/kinematic-aware-hierarchical-attention","paper_url":"https://arxiv.org/abs/2211.15868v1","paper_title":"Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos","code":"https://github.com/kyungminjin/hanet","n_code_links":1,"syntology":null},{"rank_in_archive_order":116,"model":"SMPLer-X","metrics":{"MPJPE":"75.2"},"uses_additional_data":false,"paper_date":"2023-09-29","paper":"/paper/smpler-x-scaling-up-expressive-human-pose-and","paper_url":"https://arxiv.org/abs/2309.17448v3","paper_title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","code":"https://github.com/caizhongang/SMPLer-X","n_code_links":2,"syntology":null},{"rank_in_archive_order":117,"model":"PARE + HANet (T=101)","metrics":{"Acceleration Error":"6.8","MPJPE":"77.1"},"uses_additional_data":false,"paper_date":"2022-11-29","paper":"/paper/kinematic-aware-hierarchical-attention","paper_url":"https://arxiv.org/abs/2211.15868v1","paper_title":"Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos","code":"https://github.com/kyungminjin/hanet","n_code_links":1,"syntology":null},{"rank_in_archive_order":118,"model":"MEEV","metrics":{"MPJPE":"81.74"},"uses_additional_data":false,"paper_date":"2022-10-21","paper":"/paper/meev-body-mesh-estimation-on-egocentric-video","paper_url":"https://arxiv.org/abs/2210.14165v1","paper_title":"MEEV: Body Mesh Estimation On Egocentric Video","code":"https://github.com/clovaai/meev","n_code_links":1,"syntology":null},{"rank_in_archive_order":119,"model":"HMR","metrics":{"Acceleration Error":"37.4","MPJPE":"130.0"},"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}],"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 6,885 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":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"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":28,"rows_with_any_sample_ran":24,"distinct_papers_with_graph_line":25,"distinct_papers_with_any_sample_ran":21,"samples_over_distinct_papers":{"n_ran":97,"n_unverified":102,"n_samples":199,"n_pointer_only_licence":15,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":126,"n_unverified":117,"n_samples":243,"n_pointer_only_licence":24,"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"}}}