{"url":"/dataset/cc3d","name":"CC3D","full_name":null,"description_markdown":"The CC3D dataset [1] of 3D CAD models was collected from a free online service for sharing CAD designs [2]. In total, the collected dataset contains 50k+ models, unrestricted to any category, with varying complexity from simple to highly detailed designs. These CAD models are converted to meshes, and each mesh was virtually scanned using a proprietary 3D scanning pipeline developed by Artec3D [3]. The typical size of the resulting scans is in the order of 100K points and faces, while the meshes converted from CAD models are usually more than an order of magnitude lighter. The availability of CAD-3D scan pairings, the high-resolution of meshes, and the variability of the models make the CC3D dataset stand out among other alternatives. \r\n\r\n[1] Pvdeconv: Point-voxel deconvolution for autoencoding cad construction in 3d, Cherenkova, Kseniya, Djamila Aouada, and Gleb Gusev, 2020 IEEE International Conference on Image Processing (ICIP).\r\n\r\n[2] “3dcontentcentral,” https://www.3dcontentcentral.com.\r\n\r\n[3] “Artec3d,” https://www.artec3d.com/.","description_withheld":null,"homepage":"https://cvi2.uni.lu/cc3d-dataset/","introduced_date":"2021-01-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/pvdeconv-point-voxel-deconvolution-for","title":"PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3D","first_author":"Kseniya Cherenkova","url":null},"license":null,"modalities":[],"tasks":[{"name":"CAD Reconstruction","url":"/task/cad-reconstruction","datasets_with_task":"/datasets/task/cad-reconstruction"}],"languages":[],"variants":["CC3D"],"data_loaders":[],"num_papers_in_archive":9,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cad-reconstruction-on-cc3d","task":"CAD Reconstruction","dataset_variant":"CC3D","rows":4,"metrics":["IoU","Chamfer Distance","Chamfer Distance (median)","Invalid Ratio"],"first_row_in_archive_order":{"model":"cadrille","paper":"/paper/cadrille-multi-modal-cad-reconstruction-with","metrics":{"Chamfer Distance":"1.86","Chamfer Distance (median)":"0.47","Invalid Ratio":"0.2","IoU":"67.9"},"code_links":[{"title":"col14m/cadrille","url":"https://github.com/col14m/cadrille"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/cadrille-multi-modal-cad-reconstruction-with","title":"cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning","date":"2025-05-28","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cad-recode-reverse-engineering-cad-code-from","title":"CAD-Recode: Reverse Engineering CAD Code from Point Clouds","date":"2024-12-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cad-signet-cad-language-inference-from-point","title":"CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention","date":"2024-02-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deepcad-a-deep-generative-network-for","title":"DeepCAD: A Deep Generative Network for Computer-Aided Design Models","date":"2021-05-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":2,"samples_harvested":10,"samples_ran":2,"samples_unverified":8,"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."}