{"url":"/task/monocular-3d-human-pose-estimation","name":"Monocular 3D Human Pose Estimation","slug":"monocular-3d-human-pose-estimation","description_markdown":"This task targets at 3D human pose estimation with a single RGB camera.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":101,"papers_with_code":70,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/monocular-3d-human-pose-estimation-on-human3","slug":"monocular-3d-human-pose-estimation-on-human3","dataset":"Human3.6M","dataset_url":"/dataset/human3-6m","rows_in_archive":52,"metrics":["Average MPJPE (mm)","Use Video Sequence","Frames Needed","Need Ground Truth 2D Pose","PA-MPJPE","2D detector"],"first_row_in_archive_order":{"model":"MotionBERT (Finetune)","paper_title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","paper_url":"/paper/motionbert-unified-pretraining-for-human","paper_date":"2022-10-12","arxiv_id":"2210.06551","code_links":[{"title":"Walter0807/MotionBERT","url":"https://github.com/Walter0807/MotionBERT"}],"syntology":{"n":11,"n_ran":5,"n_unverified":6,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/human3-6m","name":"Human3.6M","full_name":"","num_papers_in_archive":783},{"url":"/dataset/agora","name":"AGORA","full_name":"","num_papers_in_archive":68},{"url":"/dataset/h3wb","name":"H3WB","full_name":"Human 3.6M 3D WholeBody","num_papers_in_archive":8},{"url":"/dataset/3doh50k","name":"3DOH50K","full_name":"","num_papers_in_archive":7},{"url":"/dataset/hbw","name":"HBW","full_name":"Human Bodies in the Wild","num_papers_in_archive":7}],"subtasks":[],"parent_tasks":[{"url":"/task/3d-human-pose-estimation","name":"3D Human Pose Estimation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":70,"tagged_in_all":101,"items":[{"url":"/paper/densepose-dense-human-pose-estimation-in-the","title":"DensePose: Dense Human Pose Estimation In The Wild","date":"2018-02-01","arxiv_id":"1802.00434","repositories_listed":22,"syntology":null},{"url":"/paper/a-simple-yet-effective-baseline-for-3d-human","title":"A simple yet effective baseline for 3d human pose estimation","date":"2017-05-08","arxiv_id":"1705.03098","repositories_listed":14,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/lifting-from-the-deep-convolutional-3d-pose","title":"Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image","date":"2017-01-01","arxiv_id":"1701.00295","repositories_listed":11,"syntology":null},{"url":"/paper/3d-human-pose-estimation-in-video-with","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","date":"2018-11-28","arxiv_id":"1811.11742","repositories_listed":10,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/end-to-end-recovery-of-human-shape-and-pose","title":"End-to-end Recovery of Human Shape and Pose","date":"2017-12-18","arxiv_id":"1712.06584","repositories_listed":10,"syntology":null},{"url":"/paper/towards-3d-human-pose-estimation-in-the-wild","title":"Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach","date":"2017-04-08","arxiv_id":"1704.02447","repositories_listed":6,"syntology":null},{"url":"/paper/vibe-video-inference-for-human-body-pose-and","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","date":"2019-12-11","arxiv_id":"1912.05656","repositories_listed":5,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/semantic-graph-convolutional-networks-for-3d","title":"Semantic Graph Convolutional Networks for 3D Human Pose Regression","date":"2019-04-06","arxiv_id":"1904.03345","repositories_listed":5,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/camera-distance-aware-top-down-approach-for","title":"Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image","date":"2019-07-26","arxiv_id":"1907.11346","repositories_listed":4,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/xnect-real-time-multi-person-3d-human-pose","title":"XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera","date":"2019-07-01","arxiv_id":"1907.00837","repositories_listed":4,"syntology":null},{"url":"/paper/3d-human-pose-estimation-with-spatial-and","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","date":"2021-03-18","arxiv_id":"2103.10455","repositories_listed":3,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":8}},{"url":"/paper/uplift-and-upsample-efficient-3d-human-pose","title":"Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers","date":"2022-10-12","arxiv_id":"2210.06110","repositories_listed":2,"syntology":{"n":17,"n_ran":0,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/capturing-and-inferring-dense-full-body-human-1","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","date":"2022-06-20","arxiv_id":"2206.09553","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/icon-implicit-clothed-humans-obtained-from","title":"ICON: Implicit Clothed humans Obtained from Normals","date":"2021-12-16","arxiv_id":"2112.09127","repositories_listed":2,"syntology":null},{"url":"/paper/heuristic-weakly-supervised-3d-human-pose","title":"Heuristic Weakly Supervised 3D Human Pose Estimation","date":"2021-05-23","arxiv_id":"2105.10996","repositories_listed":2,"syntology":null},{"url":"/paper/convolutional-mesh-regression-for-single","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","date":"2019-05-08","arxiv_id":"1905.03244","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/generating-multiple-hypotheses-for-3d-human","title":"Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network","date":"2019-04-11","arxiv_id":"1904.05547","repositories_listed":2,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/neural-body-fitting-unifying-deep-learning","title":"Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation","date":"2018-08-17","arxiv_id":"1808.05942","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/unite-the-people-closing-the-loop-between-3d","title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","date":"2017-01-10","arxiv_id":"1701.02468","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/posegraf-geometric-reinforced-adaptive-fusion","title":"PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimation","date":"2025-06-17","arxiv_id":"2506.14596","repositories_listed":1,"syntology":null},{"url":"/paper/dual-stream-transformer-gcn-model-with","title":"Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation","date":"2025-04-02","arxiv_id":"2504.01764","repositories_listed":1,"syntology":null},{"url":"/paper/tcpformer-learning-temporal-correlation-with","title":"TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation","date":"2025-01-03","arxiv_id":"2501.01770","repositories_listed":1,"syntology":null},{"url":"/paper/posemamba-monocular-3d-human-pose-estimation","title":"PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model","date":"2024-08-07","arxiv_id":"2408.03540","repositories_listed":1,"syntology":null},{"url":"/paper/ktpformer-kinematics-and-trajectory-prior","title":"KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation","date":"2024-03-31","arxiv_id":"2404.00658","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":10}},{"url":"/paper/disentangled-diffusion-based-3d-human-pose","title":"Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser","date":"2024-03-07","arxiv_id":"2403.04444","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-latent-cross-channel-embedding-for","title":"Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework","date":"2024-01-18","arxiv_id":"2401.09836","repositories_listed":1,"syntology":null},{"url":"/paper/3d-lfm-lifting-foundation-model","title":"3D-LFM: Lifting Foundation Model","date":"2023-12-19","arxiv_id":"2312.11894","repositories_listed":1,"syntology":null},{"url":"/paper/manipose-manifold-constrained-multi","title":"ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation","date":"2023-12-11","arxiv_id":"2312.06386","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/motionagformer-enhancing-3d-human-pose","title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","date":"2023-10-25","arxiv_id":"2310.16288","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/double-chain-constraints-for-3d-human-pose","title":"Double-chain Constraints for 3D Human Pose Estimation in Images and Videos","date":"2023-08-10","arxiv_id":"2308.05298","repositories_listed":1,"syntology":null}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}