{"url":"/dataset/totalcapture","name":"TotalCapture","full_name":null,"description_markdown":"The **TotalCapture** dataset consists of 5 subjects performing several activities such as walking, acting, a range of motion sequence (ROM) and freestyle motions, which are recorded using 8 calibrated, static HD RGB cameras and 13 IMUs attached to head, sternum, waist, upper arms, lower arms, upper legs, lower legs and feet, however the IMU data is not required for our experiments. The dataset has publicly released foreground mattes and RGB images. Ground-truth poses are obtained using a marker-based motion capture system, with the markers are <5mm in size. All data is synchronised and operates at a framerate of 60Hz, providing ground truth poses as joint positions.\r\n\r\nSource: [Semantic Estimation of 3D Body Shape and Pose using Minimal Cameras](https://arxiv.org/abs/1908.03030)\r\nImage Source: [https://cvssp.org/data/totalcapture/](https://cvssp.org/data/totalcapture/)","description_withheld":null,"homepage":"https://cvssp.org/data/totalcapture/","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/total-capture-3d-human-pose-estimation-fusing","title":"Total capture: 3D human pose estimation fusing video and inertial sensors","first_author":"Matthew Trumble","url":null},"license":{"name":"Custom (research-only, non-commercial, attribution)","url":"https://cvssp.org/data/totalcapture/#:~:text=License"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"3D","url":"/datasets/modality/3d"}],"tasks":[{"name":"Pose Estimation","url":"/task/pose-estimation","datasets_with_task":"/datasets/task/pose-estimation"},{"name":"3D Human Pose Estimation","url":"/task/3d-human-pose-estimation","datasets_with_task":"/datasets/task/3d-human-pose-estimation"},{"name":"3D Absolute Human Pose Estimation","url":"/task/3d-absolute-human-pose-estimation","datasets_with_task":"/datasets/task/3d-absolute-human-pose-estimation"}],"languages":[],"variants":["Total Capture","TotalCapture"],"data_loaders":[],"num_papers_in_archive":57,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-human-pose-estimation-on-total-capture","task":"3D Human Pose Estimation","dataset_variant":"Total Capture","rows":14,"metrics":["Average MPJPE (mm)"],"first_row_in_archive_order":{"model":"AdaFuse","paper":"/paper/adafuse-adaptive-multiview-fusion-for","metrics":{"Average MPJPE (mm)":"19.2"},"code_links":[{"title":"zhezh/adafuse-3d-human-pose","url":"https://github.com/zhezh/adafuse-3d-human-pose"},{"title":"zhezh/occlusion_person","url":"https://github.com/zhezh/occlusion_person"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-absolute-human-pose-estimation-on-total-1","task":"3D Absolute Human Pose Estimation","dataset_variant":"Total Capture","rows":1,"metrics":["MPJPE"],"first_row_in_archive_order":{"model":"GeoFuse","paper":"/paper/fusing-wearable-imus-with-multi-view-images","metrics":{"MPJPE":"24.6"},"code_links":[{"title":"CHUNYUWANG/imu-human-pose-pytorch","url":"https://github.com/CHUNYUWANG/imu-human-pose-pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/fusepose-imu-vision-sensor-fusion-in","title":"FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation","date":"2022-08-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/adaptively-multi-view-and-temporal-fusing","title":"Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation","date":"2021-10-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/adafuse-adaptive-multiview-fusion-for","title":"AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild","date":"2020-10-26","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lightweight-multi-view-3d-pose-estimation","title":"Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation","date":"2020-04-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fusing-wearable-imus-with-multi-view-images","title":"Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach","date":"2020-03-25","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deepfuse-an-imu-aware-network-for-real-time","title":"DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image","date":"2019-12-09","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/cross-view-fusion-for-3d-human-pose","title":"Cross View Fusion for 3D Human Pose Estimation","date":"2019-09-03","rows_on_this_dataset":2,"code_links":1,"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/deep-autoencoder-for-combined-human-pose","title":"Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling","date":"2018-07-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/3d-human-pose-estimation-in-rgbd-images-for","title":"3D Human Pose Estimation in RGBD Images for Robotic Task Learning","date":"2018-03-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/total-capture-3d-human-pose-estimation-fusing","title":"Total capture: 3D human pose estimation fusing video and inertial sensors","date":"2017-09-04","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/convolutional-pose-machines","title":"Convolutional Pose Machines","date":"2016-01-30","rows_on_this_dataset":1,"code_links":50,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":11,"samples_ran":8,"samples_unverified":3,"pointer_only_for_licence":6,"papers_with_no_sample_that_ran":0,"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."}