{"id":2648,"url":"https://github.com/dae-sun/awesome-human-pose-estimation","name":"awesome-human-pose-estimation","description":"Human Mesh Recovery / Human Pose Estimation","projects_count":41,"last_synced_at":"2026-09-20T00:00:32.825Z","repository":{"id":37614327,"uuid":"496796413","full_name":"dae-sun/awesome-human-pose-estimation","owner":"dae-sun","description":"Human Mesh Recovery / Human Pose Estimation","archived":false,"fork":false,"pushed_at":"2022-08-29T11:12:47.000Z","size":1184,"stargazers_count":23,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-08-31T04:35:32.759Z","etag":null,"topics":["awesome","human-pose-estimation","mesh-reconstruction","pose-estimation"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dae-sun.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-05-26T23:02:05.000Z","updated_at":"2026-04-04T09:46:24.000Z","dependencies_parsed_at":"2022-08-19T02:01:20.547Z","dependency_job_id":null,"html_url":"https://github.com/dae-sun/awesome-human-pose-estimation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dae-sun/awesome-human-pose-estimation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dae-sun%2Fawesome-human-pose-estimation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dae-sun%2Fawesome-human-pose-estimation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dae-sun%2Fawesome-human-pose-estimation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dae-sun%2Fawesome-human-pose-estimation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dae-sun","download_url":"https://codeload.github.com/dae-sun/awesome-human-pose-estimation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dae-sun%2Fawesome-human-pose-estimation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":341189360,"owners_count":37508506,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-22T15:14:58.755Z","status":"online","status_checked_at":"2026-09-19T02:00:07.094Z","response_time":73,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-01-04T20:14:51.490Z","updated_at":"2026-09-20T00:00:32.825Z","primary_language":"Python","list_of_lists":false,"displayable":true,"categories":["3D Mesh Recovery from video","3D People Tracking","Multi-Person 2D Pose Estimation","Multi-Person 3D Pose Estimation","3D Whole-Body Mesh Recovery","Multi-Person 3D Mesh Recovery","Single-Person 3D Mesh Recovery","Single-Person 2D Pose Estimation","Backbone"],"sub_categories":["2022","2021","2020","2019"],"readme":"# awesome-human-pose-estimation [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)\n\n\n## Table of Contents\n- [Single-Person 2D Pose Estimation](#single-person-2d-pose-estimation)\n- [3D Mesh Recovery from video](#3d-mesh-recovery-from-video)\n- [3D People Tracking](#3d-people-tracking)\n- [Multi-Person 3D Mesh Recovery](#multi-person-3d-mesh-recovery)\n- [Single-Person 3D Mesh Recovery](#single-person-3d-mesh-recovery)\n- [Multi-Person 2D Pose Estimation](#multi-person-2d-pose-estimation)\n- [Multi-Person 3D Pose Estimation](#multi-person-3d-pose-estimation)\n- [Backbone](#backbone)\n\n\n## 3D Whole-Body Mesh Recovery\n### 2022\n\n##### • PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images - [[code]](https://github.com/HongwenZhang/PyMAF) [[paper]](https://arxiv.org/pdf/2207.06400.pdf) - Arxiv, PyMAF-X\n*Hongwen Zhang, Yating Tian, Yuxiang Zhang, Mengcheng Li, Liang An, Zhenan Sun, Yebin Liu*\n\n##### • Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation - [[code]](https://github.com/mks0601/Hand4Whole_RELEASE) [[paper]](https://arxiv.org/pdf/2011.11534.pdf) - CVPRW, Hand4Whole\n*Gyeongsik Moon, Hongsuk Choi, Kyoung Mu Lee*\n\n### 2021\n##### • Collaborative Regression of Expressive Bodies using Moderation - [[code]](https://github.com/YadiraF/PIXIE) [[paper]](https://arxiv.org/pdf/2105.05301.pdf) - 3DV, PIXIE\n*Yao Feng, Vasileios Choutas, Timo Bolkart, Dimitrios Tzionas, Michael J. Black*\n\n##### • FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration - [[code]](https://github.com/facebookresearch/frankmocap) [[paper]](https://arxiv.org/pdf/2008.08324.pdf) - ICCV workshop, FrankMocap\n*Ye Yuan, Umar Iqbal, Pavlo Molchanov, Kris Kitani, Jan Kautz*\n\n##### • Monocular Real-time Full Body Capture with Inter-part Correlations - [[paper]](https://arxiv.org/pdf/2012.06087.pdf) - CVPR 21, Zhou et al\n*Yuxiao Zhou, Marc Habermann, Ikhsanul Habibie, Ayush Tewari, Christian Theobalt, Feng Xu*\n\n### 2020\n##### • Whole-Body Human Pose Estimation in the Wild - [[code]](https://github.com/jin-s13/COCO-WholeBody) [[paper]](https://arxiv.org/pdf/2007.11858.pdf) - ECCV, COCO-WholeBody, (only Keypoint)\n*Jin, Sheng and Xu, Lumin and Xu, Jin and Wang, Can and Liu, Wentao and Qian, Chen and Ouyang, Wanli and Luo, Ping*\n\n##### • Monocular Expressive Body Regression through Body-Driven Attention - [[code]](https://github.com/vchoutas/expose) [[paper]](https://arxiv.org/pdf/2008.09062.pdf) - ECCV, Expose\n*Vasileios Choutas, Georgios Pavlakos, Timo Bolkart, Dimitrios Tzionas, Michael J. Black*\n\n##### • DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild - [[code]](https://github.com/naver/dope) [[paper]](https://arxiv.org/pdf/2008.09457.pdf) - ECCV, DOPE, (only Keypoint)\n*Philippe Weinzaepfel, Romain Brégier, Hadrien Combaluzier, Vincent Leroy, Grégory Rogez*\n\n\n\n\n### 2019\n##### • Expressive Body Capture: 3D Hands, Face, and Body from a Single Image -[[code]](https://github.com/vchoutas/smplx) [[paper]](https://arxiv.org/abs/1904.05866) - CVPR 19, SMPL-X\n*Pavlakos, Georgios and Choutas, Vasileios and Ghorbani, Nima and Bolkart, Timo and Osman, Ahmed A. A. and Tzionas, Dimitrios and Black, Michael J.*\n\n\n***\n## Single-Person 2D Pose Estimation\n### 2022\n##### • SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation - [[code]](https://github.com/leeyegy/SimCC) [[paper]](https://arxiv.org/pdf/2107.03332.pdf) - ECCV 22, SimCC\n\n***\n## 3D Mesh Recovery from video\n### 2022\n##### • GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras - [[code]](https://github.com/NVlabs/GLAMR) [[paper]](https://arxiv.org/pdf/2112.01524.pdf) - CVPR 22, GLAMR\n*Ye Yuan, Umar Iqbal, Pavlo Molchanov, Kris Kitani, Jan Kautz*\n\n##### • Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video - [[paper]](https://arxiv.org/pdf/2203.08534.pdf) - CVPR 22, MPS-Net\n*Wen-Li Wei, Jen-Chun Lin, Tyng-Luh Liu, Hong-Yuan Mark Liao*\n\n\n### 2021\n##### • Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video - [[code]](https://github.com/hongsukchoi/TCMR_RELEASE) [[paper]](https://arxiv.org/pdf/2011.08627.pdf) - CVPR 21, TCMR\n*Hongsuk Choi, Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee*\n\n### 2020\n##### • VIBE: Video Inference for Human Body Pose and Shape Estimation - [[code]](https://github.com/mkocabas/VIBE) [[paper]](https://arxiv.org/pdf/1912.05656.pdf) - CVPR 20, VIBE\n*Muhammed Kocabas, Nikos Athanasiou, Michael J. Black*\n***\n## 3D People Tracking\n### 2022\n##### • Tracking People by Predicting 3D Appearance, Location \u0026 Pose - [[code]](https://github.com/brjathu/PHALP) [[paper]](https://arxiv.org/pdf/2112.04477.pdf) - CVPR 22, PHALP\n*Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Jitendra Malik*\n\n### 2021\n##### • TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking - [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Reddy_TesseTrack_End-to-End_Learnable_Multi-Person_Articulated_3D_Pose_Tracking_CVPR_2021_paper.pdf) - CVPR 21, TesseTrack\n*N Dinesh Reddy, Laurent Guigues, Leonid Pishchulin, Jayan Eledath, Srinivasa G. Narasimhan*\n\n##### • Tracking People with 3D Representations - [[code]](https://github.com/brjathu/T3DP) [[paper]](https://arxiv.org/pdf/2111.07868.pdf) - NeurIPS 21, HMAR\n*Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Jitendra Malik*\n***\n\n## Multi-Person 3D Mesh Recovery\n### 2022\n##### • Putting People in their Place: Monocular Regression of 3D People in Depth - [[code]](https://github.com/Arthur151/ROMP) [[paper]](https://arxiv.org/pdf/2112.08274.pdf) [[preview]](papers/Putting_People_in_their_Place_Monocular_Regression_of_3D_People_in_Depth.pdf) - CVPR 22, BEV\n*Yu Sun, Wu Liu, Qian Bao, Yili Fu, Tao Mei, Michael J. Black*\n\n##### • Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes - [[code]](https://github.com/hongsukchoi/3DCrowdNet_RELEASE) [[paper]](https://arxiv.org/pdf/2104.07300.pdf) - CVPR 22, 3DCrowdNet\n*Hongsuk Choi, Gyeongsik Moon, JoonKyu Park, Kyoung Mu Lee*\n\n### 2021\n##### • Monocular, One-stage, Regression of Multiple 3D People - [[code]](https://github.com/Arthur151/ROMP) [[paper]](https://arxiv.org/pdf/2008.12272.pdf) - ICCV 21, ROMP\n*Yu Sun, Qian Bao, Wu Liu, Yili Fu, Michael J. Black, Tao Mei*\n\n***\n## Single-Person 3D Mesh Recovery\n### 2021\n##### • HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation - [[code]](https://github.com/Jeff-sjtu/HybrIK) [[paper]](https://arxiv.org/pdf/2011.14672.pdf) - CVPR 21, HybrIK\n*Jiefeng Li, Chao Xu, Zhicun Chen, Siyuan Bian, Lixin Yang, Cewu Lu*\n\n##### • Mesh Graphormer- [[code]](https://github.com/microsoft/MeshGraphormer) [[paper]](https://arxiv.org/pdf/2104.00272.pdf) - ICCV 21, Mesh Graphormer\n*Kevin Lin, Lijuan Wang, Zicheng Liu*\n\n##### • End-to-End Human Pose and Mesh Reconstruction with Transformers - [[code]](https://github.com/microsoft/MeshTransformer) [[paper]](https://arxiv.org/pdf/2012.09760.pdf) - CVPR 21, METRO\n*Kevin Lin, Lijuan Wang, Zicheng Liu*\n\n\n## Multi-Person 2D Pose Estimation\n\n### 2022\n##### • Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation - [[paper]](https://arxiv.org/pdf/2203.07697.pdf) - CVPR 22, DAS\n*Zitian Wang, Xuecheng Nie, Xiaochao Qu, Yunpeng Chen, Si Liu*\n\n##### • Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation - [[code]](https://github.com/cherubicXN/logocap) [[paper]](https://arxiv.org/pdf/2109.03622.pdf) - CVPR 22, LOGO-CAP\n*Nan Xue, Tianfu Wu, Gui-Song Xia, Liangpei Zhang*\n\n##### • End-to-End Multi-Person Pose Estimation with Transformers - [[code]](https://github.com/hikvision-research/opera) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Shi_End-to-End_Multi-Person_Pose_Estimation_With_Transformers_CVPR_2022_paper.pdf) - CVPR 22, PETR\n*Dahu Shi1, Xing Wei2, Liangqi Li, Ye Ren, Wenming Tan*\n\n##### • Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation - [[code]](https://github.com/mit-han-lab/litepose) [[paper]](https://arxiv.org/pdf/2205.01271.pdf) - CVPR 22, Lite Pose\n*Yihan Wang, Muyang Li, Han Cai, Wei-Ming Chen, Song Han*\n\n##### • Contextual Instance Decoupling for Robust Multi-Person Pose Estimation - [[code]](https://github.com/kennethwdk/CID) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_Contextual_Instance_Decoupling_for_Robust_Multi-Person_Pose_Estimation_CVPR_2022_paper.pdf) - CVPR 22, CID\n*Dongkai Wang, Shiliang Zhang*\n\n##### • Location-Free Human Pose Estimation - [[paper]](https://arxiv.org/pdf/2205.12619.pdf) - CVPR 22\n*Xixia Xu, Yingguo Gao, Ke Yan, Xue Lin, Qi Zou*\n\n### 2021\n\n##### • Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation - [[code]](https://github.com/wmcnally/kapao) [[paper]](https://arxiv.org/pdf/2111.08557.pdf) - Arxiv 21.11, KAPAO\n*William McNally, Kanav Vats, Alexander Wong, John McPhee*\n\n##### • Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression - [[code]](https://github.com/HRNet/DEKR) [[paper]](https://arxiv.org/pdf/2104.02300.pdf) - CVPR 21, DEKR\n*Zigang Geng, Ke Sun, Bin Xiao, Zhaoxiang Zhang, Jingdong Wang*\n\n##### • OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association - [[code]](https://github.com/openpifpaf/openpifpaf) [[paper]](https://arxiv.org/pdf/2103.02440.pdf) - Arxiv 21.03, OpenPifPaf \n*Sven Kreiss, Lorenzo Bertoni, Alexandre Alahi*\n\n##### • Human Pose Regression with Residual Log-likelihood Estimation - [[code]](https://github.com/Jeff-sjtu/res-loglikelihood-regression) [[paper]](https://arxiv.org/pdf/2107.11291.pdf) - ICCV 21, RLE \n*Jiefeng Li, Siyuan Bian, Ailing Zeng, Can Wang, Bo Pang, Wentao Liu, Cewu Lu*\n\n##### • Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation - [[code]](https://github.com/rawalkhirodkar/MIPNet) [[paper]](https://arxiv.org/pdf/2101.11223.pdf) - ICCV 21, MIPNet\n*Rawal Khirodkar, Visesh Chari, Amit Agrawal, Ambrish Tyagi*\n\n##### • Robust Pose Estimation in Crowded Scenes with Direct Pose-Level Inference - [[code]](https://github.com/kennethwdk/pinet) [[paper]](https://papers.nips.cc/paper/2021/file/31857b449c407203749ae32dd0e7d64a-Paper.pdf) - NeurIPS 21, PINet\n*Dongkai Wang, Shiliang Zhang, Gang Hua*\n\n### 2020\n##### • HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation - [[code]](https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation) [[paper]](https://arxiv.org/pdf/1908.10357.pdf) - CVPR 20, HigherHRNet\n*Bowen Cheng, Bin Xiao, Jingdong Wang, Honghui Shi, Thomas S. Huang, Lei Zhang*\n\n##### • Distribution-Aware Coordinate Representation for Human Pose Estimation - [[code]](https://github.com/ilovepose/DarkPose) [[paper]](https://arxiv.org/pdf/1910.06278.pdf) - CVPR 20, DARK\n*Feng Zhang, Xiatian Zhu, Hanbin Dai, Mao Ye, Ce Zhu*\n\n### 2019\n##### • PifPaf: Composite Fields for Human Pose Estimation - [[code]](https://github.com/openpifpaf/openpifpaf) [[paper]](https://arxiv.org/pdf/2104.02300.pdf) - CVPR 19, PifPaf \n*Sven Kreiss, Lorenzo Bertoni, Alexandre Alahi*\n\n***\n\n## Multi-Person 3D Pose Estimation\n### 2022\n##### • Single-Stage is Enough: Multi-Person Absolute 3D Pose Estimation - [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Jin_Single-Stage_Is_Enough_Multi-Person_Absolute_3D_Pose_Estimation_CVPR_2022_paper.pdf) - CVPR 22, DRM\n*Lei Jin, Chenyang Xu, Xiaojuan Wang, Yabo Xiao, Yandong Guo, Xuecheng Nie, Jian Zhao*\n\n***\n## Backbone\n### 2022\n##### • ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation - [[code]](https://github.com/vitae-transformer/vitpose) [[paper]](https://arxiv.org/pdf/2204.12484.pdf) - Arxiv 22, ViTPose\n*Yufei Xu, Jing Zhang, Qiming Zhang, Dacheng Tao*\n\n\n### 2021\n##### • HRFormer: High-Resolution Transformer for Dense Prediction - [[code]](https://github.com/HRNet/HRFormer) [[paper]](https://arxiv.org/pdf/2110.09408.pdf) - NeurIPS 21, HRFormer\n*Yuhui Yuan, Rao Fu, Lang Huang, Weihong Lin, Chao Zhang, Xilin Chen, Jingdong Wang*\n\n***\n## Datasets\n##### borrowed from 'Recovering 3D Human Mesh from Monocular Images: A Survey'\n### Rendered Datasets\n| Dataset    | # Frames | # Scenes | # Subjects | # Subjects Per Frame | In-the-wild | Mesh Type | Mesh Annotation Source |\n|------------|----------|----------|------------|----------------------|-------------|-----------|------------------------|\n| SURREAL    | 6.5M     | 2,607    | 145        | 1                    | -           | SMPL      |                        |\n| GTA-Human  | 1.4M     | -        | \u003e600       | -                    | -           | SMPL      |                        |\n| AGORA      | 17K      | -        | \u003e350       | 5~15                 | -           | SMPL-X    |                        |\n| THUman2.0  | -        | -        | ~200       | 1                    | -           | SMPL-X    |                        |\n| MultiHuman | -        | -        | ~50        | 1~3                  | -           | SMPL-X    |                        |\n\n### Marker/Sensor based MoCap\n| Dataset   | # Frames | # Scenes | # Subjects | # Subjects Per Frame | In-the-wild | Mesh Type | Mesh Annotation Source |\n|-----------|----------|----------|------------|----------------------|-------------|-----------|------------------------|\n| HumanEva  | 80K      | 1        | 4          | 1                    | -           | -         |                        |\n| Human3.6M | 3.6M     | 1        | 11         | 1                    | -           | SMPL-X    | NeuralAnnot            |\n| 3DPW      | \u003e51K     | 60       | 7          | 1~2                  | yes         | SMPL-X    | NeuralAnnot            |\n\n### Marker-less Multi-view MoCap\n| Dataset            | # Frames | # Scenes | # Subjects | # Subjects Per Frame | In-the-wild | Mesh Type | Mesh Annotation Source |\n|--------------------|----------|----------|------------|----------------------|-------------|-----------|------------------------|\n| CMU Panoptic       | 1.5M     | 1        | 40         | 3~8                  | -           | -         |                        |\n| MPI-INF-3DHP       | \u003e1.3M    | 1        | 8          | 1                    | yes         | SMPL-X    | NeuralAnnot            |\n| MuCo-3DHP          | 200K     | 1        | 8          | 1~4                  | -           | -         |                        |\n| MuPoTs-3D          | \u003e8K      | 20       | 8          | 3                    | yes         | -         |                        |\n| MannequinChallenge | 24,428   | 567      | 742        | 5                    | yes         | SMPL      |                        |\n| 3DOH50K            | 51,600   | 1        | -          | 1                    | -           | SMPL      |                        |\n| Mirrored-Human     | 1.8M     | \u003e200     | \u003e200       | \u003e=1                  | yes         | SMPL      |                        |\n| MTC                | 834K     | 1        | 40         | 1                    | -           | -         |                        |\n| EHF                | 100      | 1        | 1          | 1                    | -           | SMPL-X    |                        |\n| HUMBI              | 17.3M    | 1        | 772        | 1                    | -           | SMPL      |                        |\n| ZJU-MoCap          | -        | 1        | 9          | 1                    | -           | SMPL-X    |                        |\n\n### Datasets with pseudo 3D GT\n| Dataset      | # Frames | # Scenes | # Subjects | # Subjects Per Frame | In-the-wild | Mesh Type | Mesh Annotation Source |\n|--------------|----------|----------|------------|----------------------|-------------|-----------|------------------------|\n| LSP          | 2K       | -        | -          | 1                    | yes         | SMPL      |                        |\n| LSP-Extended | 10K      | -        | -          | 1                    | yes         | SMPL      |                        |\n| PennAction   | 77K      | 2,326    | 2,326      | 1                    | yes         | SMPL      |                        |\n| MSCOCO       | 38K      | -        | -          | \u003e=1                  | yes         | SMPL      |                        |\n| MPII         | 24,920   | 3,913    | \u003e40K       | \u003e=1                  | yes         | SMPL      |                        |\n| UP-3D        | 8,515    | -        | -          | 1                    | yes         | SMPL      |                        |\n| PoseTrack    | 66,374   | 550      | 550        | \u003e1                   | yes         | SMPL-X    | NeuralAnnot            |\n| SSP-3D       | 311      | 62       | 62         | 1                    | yes         | SMPL      |                        |\n| OCHuman      | 4,731    | -        | 8110       | \u003e1                   | yes         | SMPL      |                        |\n| MTP          | 3,731    | -        | 148        | 1                    | yes         | SMPL-X    |                        |\n***\n## Experiments\n### COCO test-dev\n - borrowed from KAPAO\n\n![ex_screenshot](./table.png)\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/dae-sun%2Fawesome-human-pose-estimation/projects"}