{"url":"/dataset/scan2cad","name":"Scan2CAD","full_name":null,"description_markdown":"**Scan2CAD** is an alignment dataset based on 1506 ScanNet scans with 97607 annotated keypoints pairs between 14225 (3049 unique) CAD models from ShapeNet and their counterpart objects in the scans. The top 3 annotated model classes are chairs, tables and cabinets which arises due to the nature of indoor scenes in ScanNet. The number of objects aligned per scene ranges from 1 to 40 with an average of 9.3.\r\n\r\nAdditionally, all ShapeNet CAD models used in the Scan2CAD dataset are annotated with their rotational symmetries: either none, 2-fold, 4-fold or infinite rotational symmetries around a canonical axis of the object.\r\n\r\nSource: [Scan2CAD: Learning CAD Model Alignment in RGB-D Scans](https://paperswithcode.com/paper/scan2cad-learning-cad-model-alignment-in-rgb/)\r\nImage Source: [Scan2CAD: Learning CAD Model Alignment in RGB-D Scans](https://paperswithcode.com/paper/scan2cad-learning-cad-model-alignment-in-rgb/)","description_withheld":null,"homepage":"https://github.com/skanti/Scan2CAD","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/scan2cad-learning-cad-model-alignment-in-rgb","title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","first_author":"Armen Avetisyan","url":null},"license":{"name":"Custom (non-commercial)","url":"https://goo.gl/forms/gJRMjzj05whyJDlO2"},"modalities":[{"name":"3D","url":"/datasets/modality/3d"},{"name":"3d meshes","url":"/datasets/modality/3d-meshes"},{"name":"Cad","url":"/datasets/modality/cad"}],"tasks":[{"name":"3D Reconstruction","url":"/task/3d-reconstruction","datasets_with_task":"/datasets/task/3d-reconstruction"}],"languages":[],"variants":["Scan2CAD"],"data_loaders":[{"repo":"https://github.com/skanti/Scan2CAD","url":"https://github.com/skanti/Scan2CAD","frameworks":["pytorch"]}],"num_papers_in_archive":72,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-reconstruction-on-scan2cad","task":"3D Reconstruction","dataset_variant":"Scan2CAD","rows":2,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Scan2CAD","paper":"/paper/scan2cad-learning-cad-model-alignment-in-rgb","metrics":{"Average Accuracy":"31.68%"},"code_links":[{"title":"skanti/Scan2CAD","url":"https://github.com/skanti/Scan2CAD"},{"title":"skanti/Scan2CAD-Annotation-Webapp","url":"https://github.com/skanti/Scan2CAD-Annotation-Webapp"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/scan2cad-learning-cad-model-alignment-in-rgb","title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","date":"2018-11-27","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/3dmatch-learning-local-geometric-descriptors","title":"3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions","date":"2016-03-27","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"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."}