{"url":"/dataset/deepcad","name":"DeepCAD","full_name":null,"description_markdown":"**DeepCAD** is a CAD dataset consisting of 179,133 models and their CAD construction sequences. It can be used to train generative models of 3D shapes.","description_withheld":null,"homepage":"https://drive.google.com/drive/folders/1PPrx5v32E-iHVg54vFjpz01W67eoP737","introduced_date":"2021-05-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/deepcad-a-deep-generative-network-for","title":"DeepCAD: A Deep Generative Network for Computer-Aided Design Models","first_author":"Rundi Wu","url":null},"license":null,"modalities":[{"name":"3D","url":"/datasets/modality/3d"}],"tasks":[{"name":"CAD Reconstruction","url":"/task/cad-reconstruction","datasets_with_task":"/datasets/task/cad-reconstruction"},{"name":"3D Assembly","url":"/task/3d-assembly","datasets_with_task":"/datasets/task/3d-assembly"}],"languages":[{"name":"Iranian Persian","url":"/datasets/language/iranian-persian"}],"variants":["DeepCAD"],"data_loaders":[],"num_papers_in_archive":35,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cad-reconstruction-on-deepcad","task":"CAD Reconstruction","dataset_variant":"DeepCAD","rows":11,"metrics":["IoU","Chamfer Distance","Camfer Distance (median)","Invalidi Ratio"],"first_row_in_archive_order":{"model":"cadrille","paper":"/paper/cadrille-multi-modal-cad-reconstruction-with","metrics":{"Camfer Distance (median)":"0.17","Chamfer Distance":"0.76","Invalidi Ratio":"0.0","IoU":"90.2"},"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"},{"leaderboard":"/sota/3d-assembly-on-deepcad","task":"3D Assembly","dataset_variant":"DeepCAD","rows":1,"metrics":["1-1"],"first_row_in_archive_order":{"model":"A","paper":"/paper/19-parameters-is-all-you-need-tiny-neural","metrics":{"1-1":"mm"},"code_links":[{"title":"abogatskiy/pelican-nano","url":"https://github.com/abogatskiy/pelican-nano"}]},"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":"2026-09-24T18:15:14+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/transcad-a-hierarchical-transformer-for-cad","title":"TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds","date":"2024-07-17","rows_on_this_dataset":1,"code_links":0,"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/draw-step-by-step-reconstructing-cad","title":"Draw Step by Step: Reconstructing CAD Construction Sequences from Point Clouds via Multimodal Diffusion.","date":"2024-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/19-parameters-is-all-you-need-tiny-neural","title":"19 Parameters Is All You Need: Tiny Neural Networks for Particle Physics","date":"2023-10-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":17,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hierarchical-neural-coding-for-controllable","title":"Hierarchical Neural Coding for Controllable CAD Model Generation","date":"2023-06-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/secad-net-self-supervised-cad-reconstruction","title":"SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations","date":"2023-03-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/extrudenet-unsupervised-inverse-sketch-and","title":"ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing","date":"2022-09-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+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/reconstructing-editable-prismatic-cad-from","title":"Reconstructing editable prismatic CAD from rounded voxel models","date":"2022-09-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/point2cyl-reverse-engineering-3d-objects-from","title":"Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders","date":"2021-12-17","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":"2026-09-24T18:15:14+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":"2026-09-24T18:15:14+00:00","papers_with_samples":6,"samples_harvested":39,"samples_ran":26,"samples_unverified":13,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":2,"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."}