{"url":"/dataset/emdb","name":"EMDB","full_name":null,"description_markdown":"EMDB contains in-the-wild  videos of human activity recorded with a hand-held iPhone. It features reference SMPL body pose and shape parameters, as well as global body root and camera trajectories. The reference 3D poses were obtained by jointly fitting SMPL to 12 body-worn electromagnetic sensors and image data. For the latter we fit a neural implicit avatar model to allow for a dense pixel-wise fitting objective.\r\n\r\nEMDB contains:\r\n\r\n* 81 sequences\r\n* 105 000 frames\r\n* 10 actors (5 female, 5 male)\r\n* Global camera trajectories\r\n* SMPL pose and shape parameters\r\n* 2D Keypoints\r\n\r\nThe dataset can be used to evaluate the following tasks:\r\n\r\n* Camera-relative 3D human pose and shape estimation from monocular videos.\r\n* Global 3D human pose and shape estimation including camera trajectories from monocular videos.\r\n* Human motion prediction.","description_withheld":null,"homepage":"https://ait.ethz.ch/emdb","introduced_date":"2023-08-31","introduced_date_note":null,"introduced_by":{"paper":"/paper/emdb-the-electromagnetic-database-of-global","title":"EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild","first_author":"Manuel Kaufmann","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"https://files.ait.ethz.ch/projects/emdb/LICENSE.txt"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"3D","url":"/datasets/modality/3d"},{"name":"RGB Video","url":"/datasets/modality/rgb-video"}],"tasks":[{"name":"3D Human Pose Estimation","url":"/task/3d-human-pose-estimation","datasets_with_task":"/datasets/task/3d-human-pose-estimation"},{"name":"Global 3D Human Pose Estimation","url":"/task/global-3d-human-pose-estimation","datasets_with_task":"/datasets/task/global-3d-human-pose-estimation"},{"name":"Human motion prediction","url":"/task/human-motion-prediction","datasets_with_task":"/datasets/task/human-motion-prediction"}],"languages":[],"variants":["EMDB"],"data_loaders":[],"num_papers_in_archive":32,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-human-pose-estimation-on-emdb","task":"3D Human Pose Estimation","dataset_variant":"EMDB","rows":13,"metrics":["Average MPJPE-PA (mm)","Average MPJPE (mm)","Average MVE (mm)","Average MVE-PA (mm)","Average MPJAE (deg)","Average MPJAE-PA (deg)","Jitter (10m/s^3)"],"first_row_in_archive_order":{"model":"TRAM","paper":"/paper/tram-global-trajectory-and-motion-of-3d","metrics":{"Average MPJPE (mm)":"74.4","Average MPJPE-PA (mm)":"45.7","Average MVE (mm)":"86.6"},"code_links":[{"title":"yufu-wang/tram","url":"https://github.com/yufu-wang/tram"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/global-3d-human-pose-estimation-on-emdb","task":"Global 3D Human Pose Estimation","dataset_variant":"EMDB","rows":1,"metrics":["Average G-MPJPE (mm)","Average G-MVE (mm)"],"first_row_in_archive_order":{"model":"GLAMR","paper":"/paper/glamr-global-occlusion-aware-human-mesh","metrics":{"Average G-MPJPE (mm)":"3193","Average G-MVE (mm)":"3203"},"code_links":[{"title":"nvlabs/glamr","url":"https://github.com/nvlabs/glamr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/biopose-biomechanically-accurate-3d-pose","title":"BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos","date":"2025-01-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/genhmr-generative-human-mesh-recovery","title":"GenHMR: Generative Human Mesh Recovery","date":"2024-12-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/tram-global-trajectory-and-motion-of-3d","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","date":"2024-03-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":13,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/wham-reconstructing-world-grounded-humans","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","date":"2023-12-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":3,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cliff-carrying-location-information-in-full","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","date":"2022-08-01","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cross-attention-of-disentangled-modalities","title":"Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers","date":"2022-07-27","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":12,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/glamr-global-occlusion-aware-human-mesh","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","date":"2021-12-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/pare-part-attention-regressor-for-3d-human","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","date":"2021-04-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/3d-human-pose-and-shape-regression-with","title":"PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop","date":"2021-03-30","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/hybrik-a-hybrid-analytical-neural-inverse","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","date":"2020-11-30","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/centerhmr-a-bottom-up-single-shot-method-for","title":"Monocular, One-stage, Regression of Multiple 3D People","date":"2020-08-27","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/human-body-model-fitting-by-learned-gradient","title":"Human Body Model Fitting by Learned Gradient Descent","date":"2020-08-19","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":46,"samples_ran":29,"samples_unverified":17,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}