{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:29:07Z","timestamp":1780392547682,"version":"3.54.1"},"reference-count":50,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Analytical center under the RF Government","award":["70-2021-00145"],"award-info":[{"award-number":["70-2021-00145"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p>\n            We propose Deep Estimators of Features (DEFs), a learning-based framework for predicting sharp geometric features in sampled 3D shapes. Differently from existing data-driven methods, which reduce this problem to feature classification, we propose to\n            <jats:italic>regress a scalar field<\/jats:italic>\n            representing the distance from point samples to the closest feature line on\n            <jats:italic>local patches.<\/jats:italic>\n            Our approach is the first that scales to massive point clouds by fusing distance-to-feature estimates obtained on individual patches.\n          <\/jats:p>\n          <jats:p>We extensively evaluate our approach against related state-of-the-art methods on newly proposed synthetic and real-world 3D CAD model benchmarks. Our approach not only outperforms these (with improvements in Recall and False Positives Rates), but generalizes to real-world scans after training our model on synthetic data and fine-tuning it on a small dataset of scanned data.<\/jats:p>\n          <jats:p>We demonstrate a downstream application, where we reconstruct an explicit representation of straight and curved sharp feature lines from range scan data.<\/jats:p>\n          <jats:p>We make code, pre-trained models, and our training and evaluation datasets available at https:\/\/github.com\/artonson\/def.<\/jats:p>","DOI":"10.1145\/3528223.3530140","type":"journal-article","created":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T21:06:27Z","timestamp":1658523987000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":46,"title":["DEF"],"prefix":"10.1145","volume":"41","author":[{"given":"Albert","family":"Matveev","sequence":"first","affiliation":[{"name":"Skoltech, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruslan","family":"Rakhimov","sequence":"additional","affiliation":[{"name":"Skoltech, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexey","family":"Artemov","sequence":"additional","affiliation":[{"name":"Skoltech, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gleb","family":"Bobrovskikh","sequence":"additional","affiliation":[{"name":"Skoltech, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vage","family":"Egiazarian","sequence":"additional","affiliation":[{"name":"Skoltech, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emil","family":"Bogomolov","sequence":"additional","affiliation":[{"name":"Skoltech, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniele","family":"Panozzo","sequence":"additional","affiliation":[{"name":"New York University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denis","family":"Zorin","sequence":"additional","affiliation":[{"name":"New York University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evgeny","family":"Burnaev","sequence":"additional","affiliation":[{"name":"Skoltech, AIRI, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,7,22]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2015.7371262"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","unstructured":"D. Bazazian and ME. Par\u00e9s. 2021. EDC-Net: Edge Detection Capsule Network for 3D Point Clouds. Applied Sciences 11 4: 1833 (2021) 1--16. 10.3390\/app11041833","DOI":"10.3390\/app11041833"},{"key":"e_1_2_2_3_1","volume-title":"Curve networks for surface reconstruction. arXiv preprint arXiv:1603.08753","author":"Cao Yuanhao","year":"2016","unstructured":"Yuanhao Cao, Liangliang Nan, and Peter Wonka. 2016. Curve networks for surface reconstruction. arXiv preprint arXiv:1603.08753 (2016)."},{"key":"e_1_2_2_4_1","volume-title":"Eurographics Italian","author":"Cignoni Paolo","unstructured":"Paolo Cignoni, Marco Callieri, Massimiliano Corsini, Matteo Dellepiane, Fabio Ganovelli, and Guido Ranzuglia. 2008. Meshlab: an open-source mesh processing tool.. In Eurographics Italian chapter conference, Vol. 2008. Salerno, Italy, 129--136."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMI.2007.32"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-008-0223-2"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2006.12.005"},{"key":"e_1_2_2_8_1","volume-title":"Note: https:\/\/github.com\/PyTorchLightning\/pytorch-lightning 3","author":"Falcon WA","year":"2019","unstructured":"WA Falcon. 2019. PyTorch Lightning. GitHub. Note: https:\/\/github.com\/PyTorchLightning\/pytorch-lightning 3 (2019)."},{"key":"e_1_2_2_9_1","volume-title":"Robust moving least-squares fitting with sharp features. ACM transactions on graphics (TOG) 24, 3","author":"Fleishman Shachar","year":"2005","unstructured":"Shachar Fleishman, Daniel Cohen-Or, and Cl\u00e1udio T Silva. 2005. Robust moving least-squares fitting with sharp features. ACM transactions on graphics (TOG) 24, 3 (2005), 544--552."},{"key":"e_1_2_2_10_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 4340--4349","author":"Gaidon Adrien","year":"2016","unstructured":"Adrien Gaidon, Qiao Wang, Yohann Cabon, and Eleonora Vig. 2016. Virtual worlds as proxy for multi-object tracking analysis. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4340--4349."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.178"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2017.05.012"},{"key":"e_1_2_2_13_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 4077--4085","author":"Handa Ankur","year":"2016","unstructured":"Ankur Handa, Viorica Patraucean, Vijay Badrinarayanan, Simon Stent, and Roberto Cipolla. 2016. Understanding real world indoor scenes with synthetic data. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4077--4085."},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1088\/0305-4470\/37\/48\/005"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811685"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_2_17_1","first-page":"1","article-title":"Towards the systematic reporting of the energy and carbon footprints of machine learning","volume":"21","author":"Henderson Peter","year":"2020","unstructured":"Peter Henderson, Jieru Hu, Joshua Romoff, Emma Brunskill, Dan Jurafsky, and Joelle Pineau. 2020. Towards the systematic reporting of the energy and carbon footprints of machine learning. Journal of Machine Learning Research 21, 248 (2020), 1--43.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3481804"},{"key":"e_1_2_2_19_1","volume-title":"Edge-aware point set resampling. ACM transactions on graphics (TOG) 32, 1","author":"Huang Hui","year":"2013","unstructured":"Hui Huang, Shihao Wu, Minglun Gong, Daniel Cohen-Or, Uri Ascher, and Hao Richard Zhang. 2013. Edge-aware point set resampling. ACM transactions on graphics (TOG) 32, 1 (2013), 9."},{"key":"e_1_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Peter J Huber et al. 1973. Robust regression: asymptotics conjectures and Monte Carlo. The annals of statistics 1 5 (1973) 799--821.","DOI":"10.1214\/aos\/1176342503"},{"key":"e_1_2_2_21_1","volume-title":"Improving Regression Performance with Distributional Losses (Proceedings of Machine Learning Research","author":"Imani Ehsan","unstructured":"Ehsan Imani and Martha White. 2018. Improving Regression Performance with Distributional Losses (Proceedings of Machine Learning Research, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). PMLR, Stockholmsm\u00e4ssan, Stockholm Sweden, 2157--2166. http:\/\/proceedings.mlr.press\/v80\/imani18a.html"},{"key":"e_1_2_2_22_1","unstructured":"Tejas Khot Shubham Agrawal Shubham Tulsiani Christoph Mertz Simon Lucey and Martial Hebert. 2019. Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency. arXiv:1905.02706 [cs.CV]"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_11"},{"key":"e_1_2_2_24_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00983"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00736"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcde.2015.07.001"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00276"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2639025"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2014.12.027"},{"key":"e_1_2_2_31_1","volume-title":"PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds. CoRR abs\/2103.02766","author":"Liu Yujia","year":"2021","unstructured":"Yujia Liu, Stefano D'Aronco, Konrad Schindler, and Jan Dirk Wegner. 2021. PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds. CoRR abs\/2103.02766 (2021). arXiv:2103.02766 https:\/\/arxiv.org\/abs\/2103.02766"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488933.3488982"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2010.261"},{"key":"e_1_2_2_34_1","volume-title":"CASCADE Technology OCCT 2021","author":"Open","year":"2021","unstructured":"Open CASCADE Technology OCCT 2021. Open CASCADE Technology OCCT. https:\/\/www.opencascade.com\/. Accessed: 2021-06-01."},{"key":"e_1_2_2_35_1","volume-title":"3D Geometric Modeling Engine","author":"Parasolid","year":"2021","unstructured":"Parasolid: 3D Geometric Modeling Engine 2021. Parasolid: 3D Geometric Modeling Engine. https:\/\/www.plm.automation.siemens.com\/global\/en\/products\/plm-components\/parasolid.html. Accessed: 2021-06-01."},{"key":"e_1_2_2_36_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32, H. Wallach, H. Larochelle, A. Beygelzimer, F. d Alche-Buc, E. Fox, and R. Garnett (Eds.). Curran Associates, Inc., 8024--8035. http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"e_1_2_2_37_1","unstructured":"Charles Ruizhongtai Qi Li Yi Hao Su and Leonidas J Guibas. 2017. Pointnet++ : Deep hierarchical feature learning on point sets in a metric space. In Advances in neural information processing systems. 5099--5108."},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2018.11.003"},{"key":"e_1_2_2_39_1","unstructured":"Range Vision Spectrum 2021. RangeVision Spectrum - a new 3D high-resolution scanner. https:\/\/rangevision.com\/en\/products\/spectrum\/. Accessed: 2021-06-01."},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_16"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.08.008"},{"key":"e_1_2_2_43_1","volume-title":"PIE-NET: Parametric Inference of Point Cloud Edges. Advances in Neural Information Processing Systems 33","author":"Wang Xiaogang","year":"2020","unstructured":"Xiaogang Wang, Yuelang Xu, Kai Xu, Andrea Tagliasacchi, Bin Zhou, Ali Mahdavi-Amiri, and Hao Zhang. 2020. PIE-NET: Parametric Inference of Point Cloud Edges. Advances in Neural Information Processing Systems 33 (2020)."},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMI.2010.32"},{"key":"e_1_2_2_46_1","volume-title":"Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Reconstruction. arXiv preprint arXiv:2010.02392","author":"Willis Karl D. D.","year":"2020","unstructured":"Karl D. D. Willis, Yewen Pu, Jieliang Luo, Hang Chu, Tao Du, Joseph G. Lambourne, Armando Solar-Lezama, and Wojciech Matusik. 2020. Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Reconstruction. arXiv preprint arXiv:2010.02392 (2020)."},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00169"},{"key":"e_1_2_2_48_1","unstructured":"Omry Yadan. 2019. Hydra - A framework for elegantly configuring complex applications. Github. https:\/\/github.com\/facebookresearch\/hydra"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_24"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1515\/eng-2019-0059"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3528223.3530140","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3528223.3530140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:48Z","timestamp":1750186968000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3528223.3530140"}},"subtitle":["deep estimation of sharp geometric features in 3D shapes"],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["10.1145\/3528223.3530140"],"URL":"https:\/\/doi.org\/10.1145\/3528223.3530140","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]},"assertion":[{"value":"2022-07-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}