{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T11:44:13Z","timestamp":1783597453384,"version":"3.55.0"},"reference-count":66,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2021,12,31]],"date-time":"2021-12-31T00:00:00Z","timestamp":1640908800000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003565","name":"MOLIT","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003565","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"MSIT","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002642","name":"Korea University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002642","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,30]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n               <jats:p>Three-dimensional (3D) computer-aided design (CAD) model reconstruction techniques are used for numerous purposes across various industries, including free-viewpoint video reconstruction, robotic mapping, tomographic reconstruction, 3D object recognition, and reverse engineering. With the development of deep learning techniques, researchers are investigating the reconstruction of 3D CAD models using learning-based methods. Therefore, we proposed a method to effectively reconstruct 3D CAD models containing machining features into 3D voxels through a 3D encoder\u2013decoder network. 3D CAD model datasets were built to train the 3D CAD model reconstruction network. For this purpose, large-scale 3D CAD models containing machining features were generated through parametric modeling and then converted into a 3D voxel format to build the training datasets. The encoder\u2013decoder network was then trained using these training datasets. Finally, the performance of the trained network was evaluated through 3D reconstruction experiments on numerous test parts, which demonstrated a high reconstruction performance with an error rate of approximately 1%.<\/jats:p>","DOI":"10.1093\/jcde\/qwab072","type":"journal-article","created":{"date-parts":[[2021,11,10]],"date-time":"2021-11-10T12:19:33Z","timestamp":1636546773000},"page":"114-127","source":"Crossref","is-referenced-by-count":29,"title":["Dataset and method for deep learning-based reconstruction of 3D CAD models containing machining features for mechanical parts"],"prefix":"10.1093","volume":"9","author":[{"given":"Hyunoh","family":"Lee","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinwon","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyungki","family":"Kim","sequence":"additional","affiliation":[{"name":"Division of Computer Science and Engineering, Jeonbuk National University, 567, Baekje-daero, Deokjin-gu, Jeonju, Jeollabuk-do 54896, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5477-0671","authenticated-orcid":false,"given":"Duhwan","family":"Mun","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,12,30]]},"reference":[{"key":"2021123110075497000_bib1","article-title":"Learning representations and generative models for 3D point clouds","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Achlioptas","year":"2018"},{"key":"2021123110075497000_bib2","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1145\/1060244.1060275","article-title":"Benchmarking CAD search techniques","volume-title":"Proceedings of the 2005 ACM Symposium on Solid and Physical Modeling","author":"Bespalov","year":"2005"},{"key":"2021123110075497000_bib3","article-title":"Generative and discriminative voxel modeling with convolutional neural networks","volume-title":"Advances in Neural Information Processing Systems","author":"Brock","year":"2016"},{"issue":"4","key":"2021123110075497000_bib4","doi-asserted-by":"crossref","first-page":"04019027","DOI":"10.1061\/(ASCE)CP.1943-5487.0000842","article-title":"Deep learning approach to point cloud scene understanding for automated scan to 3D reconstruction","volume":"33","author":"Chen","year":"2019","journal-title":"Journal of Computing in Civil Engineering"},{"key":"2021123110075497000_bib5","first-page":"5828","article-title":"ScanNet: Richly-annotated 3d reconstructions of indoor scenes","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Dai","year":"2017"},{"key":"2021123110075497000_bib6","first-page":"5868","article-title":"Shape completion using 3d-encoder-predictor CNNs and shape synthesis","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Dai","year":"2017"},{"issue":"2","key":"2021123110075497000_bib7","doi-asserted-by":"crossref","first-page":"359","DOI":"10.5194\/esurf-4-359-2016","article-title":"Image-based surface reconstruction in geomorphometry\u2013merits, limits and developments","volume":"4","author":"Eltner","year":"2016","journal-title":"Earth Surface Dynamics"},{"key":"2021123110075497000_bib8","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.264","article-title":"A point set generation network for 3D object reconstruction from a single image","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Fan","year":"2017"},{"issue":"1","key":"2021123110075497000_bib9","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1007\/s11042-020-09722-8","article-title":"Single image 3D object reconstruction based on deep learning: A review","volume":"80","author":"Fu","year":"2021","journal-title":"Multimedia Tools and Applications"},{"key":"2021123110075497000_bib10","first-page":"489","article-title":"Point-to-point regression pointnet for 3d hand pose estimation","volume-title":"Lecture Notes in Computer Science. Proceedings of the European Conference on Computer Vision","author":"Ge","year":"2018"},{"key":"2021123110075497000_bib11","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.cagd.2018.03.024","article-title":"Learning localized features in 3D CAD models for manufacturability analysis of drilled holes","volume":"62","author":"Ghadai","year":"2018","journal-title":"Computer Aided Geometric Design"},{"issue":"2","key":"2021123110075497000_bib12","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1093\/jcde\/qwab011","article-title":"Airfoil profile reconstruction from unorganized noisy point cloud data","volume":"8","author":"Ghorbani","year":"2021","journal-title":"Journal of Computational Design and Engineering"},{"key":"2021123110075497000_bib13","article-title":"Generative adversarial networks","volume-title":"Advances in Neural Information Processing Systems","author":"Goodfellow","year":"2014"},{"key":"2021123110075497000_bib14","author":"HDF Group","year":"1997"},{"key":"2021123110075497000_bib15","first-page":"2626","article-title":"Recurrent slice networks for 3d segmentation of point clouds","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Huang","year":"2018"},{"issue":"3","key":"2021123110075497000_bib16","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.jcde.2018.11.002","article-title":"A parametric morphing method for generating structured meshes for marine free surface flow applications with plane symmetry","volume":"6","author":"Immonen","year":"2019","journal-title":"Journal of Computational Design and Engineering"},{"issue":"9","key":"2021123110075497000_bib17","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1016\/j.cad.2006.06.007","article-title":"Developing an engineering shape benchmark for CAD models","volume":"38","author":"Jayanti","year":"2006","journal-title":"Computer-Aided Design"},{"key":"2021123110075497000_bib18","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.future.2018.05.033","article-title":"An improved NBA-based STEP design intention feature recognition","volume":"88","author":"Jian","year":"2018","journal-title":"Future Generation Computer Systems"},{"key":"2021123110075497000_bib19","article-title":"Mo-Net: Flavor the moments in learning to classify shapes","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops","author":"Joseph-Rivlin","year":"2018"},{"key":"2021123110075497000_bib20","first-page":"3779","article-title":"3D shape segmentation with projective convolutional networks","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Kalogerakis","year":"2017"},{"key":"2021123110075497000_bib22","doi-asserted-by":"crossref","first-page":"103320","DOI":"10.1016\/j.compind.2020.103320","article-title":"Deep-learning-based retrieval of piping component catalogs for plant 3D CAD model reconstruction","volume":"123","author":"Kim","year":"2020","journal-title":"Computers in Industry"},{"key":"2021123110075497000_bib23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58523-5_11","article-title":"A large-scale annotated mechanical components benchmark for classification and retrieval tasks with deep neural networks","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Kim","year":"2020"},{"issue":"1","key":"2021123110075497000_bib21","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1093\/jcde\/qwaa087","article-title":"Lifecycle management of component catalogs based on a neutral model to support seamless integration with plant 3D design","volume":"8","author":"Kim","year":"2021","journal-title":"Journal of Computational Design and Engineering"},{"key":"2021123110075497000_bib24","article-title":"Adam: A method for stochastic optimization","volume-title":"International Conference on Learning Representations","author":"Kingma","year":"2015"},{"key":"2021123110075497000_bib25","first-page":"863","article-title":"Escape from cells: Deep kd-networks for the recognition of 3d point cloud models","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Klokov","year":"2017"},{"issue":"6","key":"2021123110075497000_bib26","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1093\/jcde\/qwaa056","article-title":"Registration method for maintenance-work support based on augmented-reality-model generation from drawing data","volume":"7","author":"Lee","year":"2020","journal-title":"Journal of Computational Design and Engineering"},{"key":"2021123110075497000_bib27","author":"Lee","year":"2021"},{"issue":"1","key":"2021123110075497000_bib28","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1093\/jcde\/qwaa072","article-title":"3D reconstruction of as-built model of plant piping system from point clouds and port information","volume":"8","author":"Lee","year":"2021","journal-title":"Journal of Computational Design and Engineering"},{"key":"2021123110075497000_bib29","first-page":"1","article-title":"Variational Autoencoder for 3D Voxel Compression","volume-title":"2020 35th International Conference on Image and Vision Computing New Zealand","author":"Liu","year":"2020"},{"key":"2021123110075497000_bib30","doi-asserted-by":"crossref","first-page":"22711","DOI":"10.1109\/ACCESS.2021.3055826","article-title":"A convolutional neural network approach to the classification of engineering models","volume":"9","author":"Manda","year":"2021","journal-title":"IEEE Access"},{"key":"2021123110075497000_bib31","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.cag.2021.07.001","article-title":"\u2018CADSketchNet\u2019-An annotated sketch dataset for 3D CAD model retrieval with deep neural networks","volume":"99","author":"Manda","year":"2021","journal-title":"Computers and Graphics"},{"key":"2021123110075497000_bib32","first-page":"922","article-title":"VoxNet: A 3D convolutional neural network for real-time object recognition","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems","author":"Maturana","year":"2015"},{"key":"2021123110075497000_bib33","first-page":"1","article-title":"Predicting part mass, required support material, and build time via autoencoded voxel patterns","volume-title":"29th Annual International Solid Freeform Fabrication Symposium","author":"McComb","year":"2018"},{"key":"2021123110075497000_bib34","first-page":"4460","article-title":"Occupancy networks: Learning 3d reconstruction in function space","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Mescheder","year":"2019"},{"key":"2021123110075497000_bib35","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.cag.2019.03.016","article-title":"Autoencoder-based part clustering for part-in-whole retrieval of CAD models","volume":"81","author":"Muraleedharan","year":"2019","journal-title":"Computers and Graphics"},{"key":"2021123110075497000_bib36","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1016\/j.promfg.2020.05.130","article-title":"Deep learning-based approach for identifying conventional machining processes from CAD data","volume":"48","author":"Peddireddy","year":"2020","journal-title":"Procedia Manufacturing"},{"key":"2021123110075497000_bib37","doi-asserted-by":"crossref","first-page":"1336","DOI":"10.1016\/j.jmapro.2021.02.034","article-title":"Identifying manufacturability and machining processes using deep 3D convolutional networks","volume":"64","author":"Peddireddy","year":"2021","journal-title":"Journal of Manufacturing Processes"},{"key":"2021123110075497000_bib38","first-page":"5648","article-title":"Volumetric and multi-view CNNs for object classification on 3d data","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Qi","year":"2016"},{"key":"2021123110075497000_bib39","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Conference on Neural Information Processing Systems (NIPS)","author":"Qi","year":"2017"},{"key":"2021123110075497000_bib40","first-page":"725","article-title":"Generating 3D faces using convolutional mesh autoencoders","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Ranjan","year":"2018"},{"key":"2021123110075497000_bib41","first-page":"3577","article-title":"OctNet: Learning deep 3D representations at high resolutions","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Riegler","year":"2017"},{"key":"2021123110075497000_bib42","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Ronneberger","year":"2015"},{"key":"2021123110075497000_bib43","first-page":"236","article-title":"Vconv-dae: Deep volumetric shape learning without object labels","volume-title":"European Conference on Computer Vision","author":"Sharma","year":"2016"},{"issue":"5","key":"2021123110075497000_bib44","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1007\/s10845-020-01533-w","article-title":"A novel learning-based feature recognition method using multiple sectional view representation","volume":"31","author":"Shi","year":"2020","journal-title":"Journal of Intelligent Manufacturing"},{"key":"2021123110075497000_bib46","first-page":"1746","article-title":"Semantic scene completion from a single depth image","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Song","year":"2017"},{"issue":"1","key":"2021123110075497000_bib45","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1093\/jcde\/qwaa086","article-title":"Unorganized point classification for robust NURBS surface reconstruction using a point-based neural network","volume":"8","author":"Song","year":"2021","journal-title":"Journal of Computational Design and Engineering"},{"key":"2021123110075497000_bib47","first-page":"945","article-title":"Multi-view convolutional neural networks for 3d shape recognition","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Su","year":"2015"},{"key":"2021123110075497000_bib48","first-page":"186","article-title":"Multi-view harmonized bilinear network for 3d object recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Yu","year":"2018"},{"key":"2021123110075497000_bib49","article-title":"Lecture 6.5\u2013RmsProp: Divide the gradient by a running average of its recent magnitude","volume-title":"COURSERA: Neural networks for machine learning","author":"Tieleman","year":"2012"},{"key":"2021123110075497000_bib50","first-page":"2626","article-title":"Multi-view supervision for single-view reconstruction via differentiable ray consistency","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Tulsiani","year":"2017"},{"key":"2021123110075497000_bib52","doi-asserted-by":"crossref","DOI":"10.5244\/C.31.64","article-title":"Dominant set clustering and pooling for multi-view 3d object recognition","volume-title":"Proceedings of the British Machine Vision Conference","author":"Wang","year":"2017"},{"issue":"4","key":"2021123110075497000_bib55","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450626.3459787","article-title":"O-CNN: Octree-based convolutional neural networks for 3d shape analysis","volume":"36","author":"Wang","year":"2017","journal-title":"ACM Transactions on Graphics"},{"key":"2021123110075497000_bib53","first-page":"52","article-title":"Pixel2Mesh: Generating 3D mesh models from single RGB images","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Wang","year":"2018"},{"key":"2021123110075497000_bib54","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.cag.2017.07.030","article-title":"3d shape segmentation via shape fully convolutional networks","volume":"70","author":"Wang","year":"2018","journal-title":"Computers and Graphics"},{"key":"2021123110075497000_bib51","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.neucom.2018.09.075","article-title":"NormalNet: A voxel-based CNN for 3D object classification and retrieval","volume":"323","author":"Wang","year":"2019","journal-title":"Neurocomputing"},{"key":"2021123110075497000_bib56","article-title":"Fusion 360 gallery: A dataset and environment for programmatic CAD reconstruction","volume-title":"International Conference on Learning Representations","author":"Willis","year":"2021"},{"key":"2021123110075497000_bib58","first-page":"1912","article-title":"3D ShapeNets: A deep representation for volumetric shapes","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Wu","year":"2015"},{"key":"2021123110075497000_bib57","article-title":"Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling","volume-title":"Advances in Neural Information Processing Systems","author":"Wu","year":"2016"},{"key":"2021123110075497000_bib59","article-title":"DISN: Deep implicit surface network for high-quality single-view 3d reconstruction","volume-title":"Advances in Neural Information Processing Systems","author":"Xu","year":"2019"},{"key":"2021123110075497000_bib60","first-page":"6584","article-title":"SyncSpecCNN: Synchronized spectral CNN for 3d shape segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Yi","year":"2017"},{"key":"2021123110075497000_bib61","first-page":"2790","article-title":"Pu-net: Point cloud upsampling network","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Yu","year":"2018"},{"key":"2021123110075497000_bib62","first-page":"3391","article-title":"Deep sets","volume-title":"Conference on Neural Information Processing Systems (NIPS)","author":"Zaheer","year":"2017"},{"key":"2021123110075497000_bib65","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.cad.2018.03.006","article-title":"Featurenet: Machining feature recognition based on 3d convolution neural network","volume":"101","author":"Zhang","year":"2018","journal-title":"Computer-Aided Design"},{"issue":"4","key":"2021123110075497000_bib63","doi-asserted-by":"crossref","first-page":"2335","DOI":"10.1109\/TII.2019.2943195","article-title":"View-based 3d CAD model retrieval with deep residual networks","volume":"16","author":"Zhang","year":"2019","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"1","key":"2021123110075497000_bib64","doi-asserted-by":"crossref","first-page":"57","DOI":"10.3233\/ICA-190608","article-title":"Pointwise geometric and semantic learning network on 3D point clouds","volume":"27","author":"Zhang","year":"2020","journal-title":"Integrated Computer-Aided Engineering"},{"issue":"4","key":"2021123110075497000_bib66","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1016\/j.jcde.2019.03.002","article-title":"Variational B-rep model analysis for direct modeling using geometric perturbation","volume":"6","author":"Zou","year":"2019","journal-title":"Journal of Computational Design and Engineering"}],"container-title":["Journal of Computational Design and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/9\/1\/114\/41988785\/qwab072.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/9\/1\/114\/41988785\/qwab072.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,31]],"date-time":"2021-12-31T10:09:58Z","timestamp":1640945398000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/9\/1\/114\/6490312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,30]]},"references-count":66,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12,30]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwab072","relation":{},"ISSN":["2288-5048"],"issn-type":[{"value":"2288-5048","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,2]]},"published":{"date-parts":[[2021,12,30]]}}}