{"url":"/dataset/cape","name":"CAPE","full_name":"Clothed Auto Person Encoding","description_markdown":"The CAPE dataset is a 3D dynamic dataset of clothed humans, featuring:\r\n\r\n- 3D mesh registrations of accurate scans of clothed people in motion, captured at 60 FPS;\r\n- Consistent SMPL mesh topology, all frames in correspondence;\r\n- Precise, captured minimally clothed body shape under clothing;\r\n- Clothed bodies of large pose variations;\r\n- Both posed and unposed (i.e. in canonical pose) clothed body for each frame;\r\n- SMPL body pose parameters for each frame;\r\n- (New!) High-quality raw scan data of several subjects and sequences along with texture is available. Please first register as a user and send us your request.","description_withheld":null,"homepage":"https://cape.is.tue.mpg.de/dataset.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Custom","url":"https://cape.is.tue.mpg.de/license.html"},"modalities":[{"name":"3d meshes","url":"/datasets/modality/3d-meshes"}],"tasks":[{"name":"3D Human Reconstruction","url":"/task/3d-human-reconstruction","datasets_with_task":"/datasets/task/3d-human-reconstruction"}],"languages":[],"variants":["CAPE"],"data_loaders":[{"repo":"https://github.com/yuliangxiu/icon","url":"https://github.com/YuliangXiu/ICON/blob/master/docs/evaluation.md","frameworks":["pytorch"]},{"repo":"https://github.com/QianliM/CAPE","url":"https://cape.is.tue.mpg.de/","frameworks":["pytorch"]}],"num_papers_in_archive":10,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-human-reconstruction-on-cape","task":"3D Human Reconstruction","dataset_variant":"CAPE","rows":4,"metrics":["Chamfer (cm)","P2S (cm)","NC"],"first_row_in_archive_order":{"model":"ICON","paper":"/paper/icon-implicit-clothed-humans-obtained-from","metrics":{"Chamfer (cm)":"1.142","NC":"0.066","P2S (cm)":"1.065"},"code_links":[{"title":"yuliangxiu/icon","url":"https://github.com/yuliangxiu/icon"},{"title":"otaheri/GOAL","url":"https://github.com/otaheri/GOAL"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/icon-implicit-clothed-humans-obtained-from","title":"ICON: Implicit Clothed humans Obtained from Normals","date":"2021-12-16","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/pamir-parametric-model-conditioned-implicit","title":"PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction","date":"2020-07-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pifuhd-multi-level-pixel-aligned-implicit","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","date":"2020-04-01","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/pifu-pixel-aligned-implicit-function-for-high","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","date":"2019-05-13","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"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."}