{"url":"/dataset/ssp-3d","name":"SSP-3D","full_name":"Sports Shape and Pose 3D","description_markdown":"SSP-3D is an evaluation dataset consisting of 311 images of sportspersons in tight-fitted clothes, with a variety of body shapes and poses. The images were collected from the [Sports-1M dataset](https://cs.stanford.edu/people/karpathy/deepvideo/). SSP-3D is intended for use as a benchmark for body **shape** prediction methods. Pseudo-ground-truth 3D shape labels (using the SMPL body model) were obtained via multi-frame optimisation with shape consistency between frames, as described [here](https://arxiv.org/abs/2009.10013).","description_withheld":null,"homepage":"https://github.com/akashsengupta1997/SSP-3D","introduced_date":"2020-09-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/synthetic-training-for-accurate-3d-human-pose","title":"Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild","first_author":"Akash Sengupta","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"3D","url":"/datasets/modality/3d"},{"name":"3d meshes","url":"/datasets/modality/3d-meshes"}],"tasks":[{"name":"3D Human Pose Estimation","url":"/task/3d-human-pose-estimation","datasets_with_task":"/datasets/task/3d-human-pose-estimation"},{"name":"3D Human Reconstruction","url":"/task/3d-human-reconstruction","datasets_with_task":"/datasets/task/3d-human-reconstruction"},{"name":"3D Human Shape Estimation","url":"/task/3d-human-shape-estimation","datasets_with_task":"/datasets/task/3d-human-shape-estimation"}],"languages":[],"variants":["SSP-3D"],"data_loaders":[],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-human-shape-estimation-on-ssp-3d","task":"3D Human Shape Estimation","dataset_variant":"SSP-3D","rows":11,"metrics":["PVE-T-SC","PVE-T","mIOU"],"first_row_in_archive_order":{"model":"Hierarchical Probabilistic Humans","paper":"/paper/hierarchical-kinematic-probability","metrics":{"PVE-T-SC":"13.6"},"code_links":[{"title":"akashsengupta1997/hierarchicalprobabilistic3dhuman","url":"https://github.com/akashsengupta1997/hierarchicalprobabilistic3dhuman"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/shape-of-you-precise-3d-shape-estimations-for","title":"Shape of You: Precise 3D shape estimations for diverse body types","date":"2023-04-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/accurate-3d-body-shape-regression-using-1","title":"Accurate 3D Body Shape Regression using Metric and Semantic Attributes","date":"2022-06-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-kinematic-probability","title":"Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild","date":"2021-10-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":6,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lasor-learning-accurate-3d-human-pose-and","title":"LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering","date":"2021-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":2,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/everybody-is-unique-towards-unbiased-human","title":"Everybody Is Unique: Towards Unbiased Human Mesh Recovery","date":"2021-07-13","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/probabilistic-3d-human-shape-and-pose","title":"Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild","date":"2021-03-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/synthetic-training-for-accurate-3d-human-pose","title":"Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild","date":"2020-09-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":2,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-to-reconstruct-3d-human-pose-and","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","date":"2019-09-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/end-to-end-recovery-of-human-shape-and-pose","title":"End-to-end Recovery of Human Shape and Pose","date":"2017-12-18","rows_on_this_dataset":2,"code_links":10,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":29,"samples_ran":10,"samples_unverified":19,"pointer_only_for_licence":0,"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."}