{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:11:25Z","timestamp":1784268685974,"version":"3.55.0"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T00:00:00Z","timestamp":1721347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2024,7,19]]},"abstract":"<jats:p>\n            This paper presents\n            <jats:italic>BrepGen<\/jats:italic>\n            , a diffusion-based generative approach that directly outputs a Boundary representation (B-rep) Computer-Aided Design (CAD) model.\n            <jats:italic>BrepGen<\/jats:italic>\n            represents a B-rep model as a novel structured latent geometry in a hierarchical tree. With the root node representing a whole CAD solid, each element of a B-rep model (i.e., a face, an edge, or a vertex) progressively turns into a child-node from top to bottom. B-rep geometry information goes into the nodes as the global bounding box of each primitive along with a latent code describing the local geometric shape. The B-rep topology information is implicitly represented by node duplication. When two faces share an edge, the edge curve will appear twice in the tree, and a T-junction vertex with three incident edges appears six times in the tree with identical node features. Starting from the root and progressing to the leaf,\n            <jats:italic>BrepGen<\/jats:italic>\n            employs Transformer-based diffusion models to sequentially denoise node features while duplicated nodes are detected and merged, recovering the B-Rep topology information. Extensive experiments show that\n            <jats:italic>BrepGen<\/jats:italic>\n            advances the task of CAD B-rep generation, surpassing existing methods on various benchmarks. Results on our newly collected furniture dataset further showcase its exceptional capability in generating complicated geometry. While previous methods were limited to generating simple prismatic shapes,\n            <jats:italic>BrepGen<\/jats:italic>\n            incorporates free-form and doubly-curved surfaces for the first time. Additional applications of\n            <jats:italic>BrepGen<\/jats:italic>\n            include CAD autocomplete and design interpolation. The code, pretrained models, and dataset are available at https:\/\/github.com\/samxuxiang\/BrepGen.\n          <\/jats:p>","DOI":"10.1145\/3658129","type":"journal-article","created":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T14:47:57Z","timestamp":1721400477000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":62,"title":["BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3437-1470","authenticated-orcid":false,"given":"Xiang","family":"Xu","sequence":"first","affiliation":[{"name":"Simon Fraser University, Burnaby, Canada"},{"name":"Autodesk Research, Burnaby, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9892-1945","authenticated-orcid":false,"given":"Joseph","family":"Lambourne","sequence":"additional","affiliation":[{"name":"Autodesk, London, United Kingdom"},{"name":"Autodesk Research, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6314-6136","authenticated-orcid":false,"given":"Pradeep","family":"Jayaraman","sequence":"additional","affiliation":[{"name":"Autodesk, Toronto, Canada"},{"name":"Autodesk Research, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8067-1927","authenticated-orcid":false,"given":"Zhengqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6990-2294","authenticated-orcid":false,"given":"Karl","family":"Willis","sequence":"additional","affiliation":[{"name":"Autodesk, San Francisco, United States of America"},{"name":"Autodesk Research, San Francisco, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9775-4512","authenticated-orcid":false,"given":"Yasutaka","family":"Furukawa","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, Canada"},{"name":"Autodesk, Burnaby, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,19]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Poly-Diff: Generating 3D Polygonal Meshes with Diffusion Models. arXiv preprint arXiv:2312.11417","author":"Alliegro Antonio","year":"2023","unstructured":"Antonio Alliegro, Yawar Siddiqui, Tatiana Tommasi, and Matthias Nie\u00dfner. 2023. Poly-Diff: Generating 3D Polygonal Meshes with Diffusion Models. arXiv preprint arXiv:2312.11417 (2023)."},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.4043211"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/325334.325218"},{"key":"e_1_2_2_4_1","article-title":"HG-CAD: Hierarchical Graph Learning for Material Prediction and Recommendation in Computer-Aided Design","volume":"24","author":"Bian Shijie","year":"2023","unstructured":"Shijie Bian, Daniele Grandi, Tianyang Liu, Pradeep Kumar Jayaraman, Karl Willis, Elliot Sadler, Bodia Borijin, Thomas Lu, Richard Otis, Nhut Ho, and Bingbing Li. 2023. HG-CAD: Hierarchical Graph Learning for Material Prediction and Recommendation in Computer-Aided Design. Journal of Computing and Information Science in Engineering 24, 1 (10 2023), 011007.","journal-title":"Journal of Computing and Information Science in Engineering"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2020-22355"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2020-22355"},{"key":"e_1_2_2_7_1","volume-title":"Computer graphics forum","author":"Chen Ding-Yun","unstructured":"Ding-Yun Chen, Xiao-Pei Tian, Yu-Te Shen, and Ming Ouhyoung. 2003. On visual similarity based 3D model retrieval. In Computer graphics forum, Vol. 22. Wiley Online Library, 223--232."},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00012"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275006"},{"key":"e_1_2_2_10_1","unstructured":"Kevin Ellis Maxwell Nye Yewen Pu Felix Sosa Josh Tenenbaum and Armando Solar-Lezama. 2019. Write execute assess: Program synthesis with a repl. In Advances in Neural Information Processing Systems (NeurIPS). 9169--9178."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530078"},{"key":"e_1_2_2_12_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840--6851."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3586589.3586636"},{"key":"e_1_2_2_14_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_2_2_15_1","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume":"34","author":"Hoogeboom Emiel","year":"2021","unstructured":"Emiel Hoogeboom, Didrik Nielsen, Priyank Jaini, Patrick Forr\u00e9, and Max Welling. 2021. Argmax flows and multinomial diffusion: Learning categorical distributions. Advances in Neural Information Processing Systems 34 (2021), 12454--12465.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555394"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2203.13944"},{"key":"e_1_2_2_18_1","volume-title":"UV-Net: Learning From Boundary Representations. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 11703--11712","author":"Jayaraman Pradeep Kumar","year":"2021","unstructured":"Pradeep Kumar Jayaraman, Aditya Sanghi, Joseph G. Lambourne, Karl D.D. Willis, Thomas Davies, Hooman Shayani, and Nigel Morris. 2021. UV-Net: Learning From Boundary Representations. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 11703--11712."},{"key":"e_1_2_2_19_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478513.3480562","article-title":"Automate: A dataset and learning approach for automatic mating of cad assemblies","volume":"40","author":"Jones Benjamin","year":"2021","unstructured":"Benjamin Jones, Dalton Hildreth, Duowen Chen, Ilya Baran, Vladimir G Kim, and Adriana Schulz. 2021. Automate: A dataset and learning approach for automatic mating of cad assemblies. ACM Transactions on Graphics (TOG) 40, 6 (2021), 1--18.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02043"},{"key":"e_1_2_2_21_1","unstructured":"Kacper Kania Maciej Zi\u0119ba and Tomasz Kajdanowicz. 2020. UCSG-Net-Unsupervised Discovering of Constructive Solid Geometry Tree. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_2_2_22_1","volume-title":"ABC: A Big CAD Model Dataset For Geometric Deep Learning. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Koch Sebastian","year":"2019","unstructured":"Sebastian Koch, Albert Matveev, Zhongshi Jiang, Francis Williams, Alexey Artemov, Evgeny Burnaev, Marc Alexa, Denis Zorin, and Daniele Panozzo. 2019. ABC: A Big CAD Model Dataset For Geometric Deep Learning. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01258"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00276"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01613"},{"key":"e_1_2_2_26_1","volume-title":"Ali Mahdavi-Amiri, and Manolis Savva.","author":"Liu Jiayi","year":"2023","unstructured":"Jiayi Liu, Hou In Ivan Tam, Ali Mahdavi-Amiri, and Manolis Savva. 2023. CAGE: Controllable Articulation GEneration. arXiv preprint arXiv:2312.09570 (2023)."},{"key":"e_1_2_2_27_1","volume-title":"Pseudo numerical methods for diffusion models on manifolds. arXiv preprint arXiv:2202.09778","author":"Liu Luping","year":"2022","unstructured":"Luping Liu, Yi Ren, Zhijie Lin, and Zhou Zhao. 2022. Pseudo numerical methods for diffusion models on manifolds. arXiv preprint arXiv:2202.09778 (2022)."},{"key":"e_1_2_2_28_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(78)90051-8"},{"key":"e_1_2_2_31_1","volume-title":"2nd Summit on Advances in Programming Languages (SNAPL","author":"Nandi Chandrakana","year":"2017","unstructured":"Chandrakana Nandi, Anat Caspi, Dan Grossman, and Zachary Tatlock. 2017. Programming language tools and techniques for 3D printing. In 2nd Summit on Advances in Programming Languages (SNAPL 2017). Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik."},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236794"},{"key":"e_1_2_2_33_1","volume-title":"International Conference on Machine Learning (ICML). PMLR, 7220--7229","author":"Nash Charlie","year":"2020","unstructured":"Charlie Nash, Yaroslav Ganin, SM Ali Eslami, and Peter Battaglia. 2020. Polygen: An autoregressive generative model of 3d meshes. In International Conference on Machine Learning (ICML). PMLR, 7220--7229."},{"key":"e_1_2_2_34_1","unstructured":"Onshape. 2012. http:\/\/www.onshape.com."},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01225"},{"key":"e_1_2_2_36_1","unstructured":"Daxuan Ren Jianmin Zheng Jianfei Cai Jiatong Li and Junzhe Zhang. 2022. ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing. In ECCV."},{"key":"e_1_2_2_37_1","volume-title":"Karl DD Willis, and Jiajun Wu","author":"Ritchie Daniel","year":"2023","unstructured":"Daniel Ritchie, Paul Guerrero, R Kenny Jones, Niloy J Mitra, Adriana Schulz, Karl DD Willis, and Jiajun Wu. 2023. Neurosymbolic Models for Computer Graphics. In Computer Graphics Forum, Vol. 42. Wiley Online Library, 545--568."},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00529"},{"key":"e_1_2_2_40_1","volume-title":"CSGNet: Neural Shape Parser for Constructive Solid Geometry. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Sharma Gopal","year":"2018","unstructured":"Gopal Sharma, Rishabh Goyal, Difan Liu, Evangelos Kalogerakis, and Subhransu Maji. 2018. CSGNet: Neural Shape Parser for Constructive Solid Geometry. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Gopal Sharma Difan Liu Evangelos Kalogerakis Subhransu Maji Siddhartha Chaudhuri and Radom\u00edr M\u011bch. 2020. ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds. arXiv:2003.12181 [cs.CV]","DOI":"10.1007\/978-3-030-58571-6_16"},{"key":"e_1_2_2_42_1","volume-title":"Meshgpt: Generating triangle meshes with decoder-only transformers. arXiv preprint arXiv:2311.15475","author":"Siddiqui Yawar","year":"2023","unstructured":"Yawar Siddiqui, Antonio Alliegro, Alexey Artemov, Tatiana Tommasi, Daniele Sirigatti, Vladislav Rosov, Angela Dai, and Matthias Nie\u00dfner. 2023. Meshgpt: Generating triangle meshes with decoder-only transformers. arXiv preprint arXiv:2311.15475 (2023)."},{"key":"e_1_2_2_43_1","volume-title":"Learning Manifold Patch-Based Representations of Man-Made Shapes. In International Conference on Learning Representations (ICLR).","author":"Smirnov Dmitriy","year":"2021","unstructured":"Dmitriy Smirnov, Mikhail Bessmeltsev, and Justin Solomon. 2021. Learning Manifold Patch-Based Representations of Man-Made Shapes. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_2_44_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Tian Yonglong","year":"2019","unstructured":"Yonglong Tian, Andrew Luo, Xingyuan Sun, Kevin Ellis, William T. Freeman, Joshua B. Tenenbaum, and Jiajun Wu. 2019. Learning to Infer and Execute 3D Shape Programs. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_2_2_46_1","volume-title":"Pointer networks. Advances in Neural Information Processing Systems (NeurIPS)","author":"Vinyals Oriol","year":"2015","unstructured":"Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. Advances in Neural Information Processing Systems (NeurIPS) (2015)."},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00167"},{"key":"e_1_2_2_48_1","volume-title":"Advances in Neural Information Processing Systems","volume":"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. In Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 20167--20178."},{"key":"e_1_2_2_49_1","volume-title":"Topological structures for geometric modeling","author":"Weiler K.J.","unstructured":"K.J. Weiler. 1986. Topological structures for geometric modeling. University Microfilms."},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01539"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00239"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459818"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00670"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3620009"},{"key":"e_1_2_2_55_1","volume-title":"Inferring CAD Modeling Sequences Using Zone Graphs. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 6062--6070","author":"Xu Xianghao","year":"2021","unstructured":"Xianghao Xu, Wenzhe Peng, Chin-Yi Cheng, Karl D.D. Willis, and Daniel Ritchie. 2021. Inferring CAD Modeling Sequences Using Zone Graphs. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 6062--6070."},{"key":"e_1_2_2_56_1","volume-title":"SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks. In International Conference on Machine Learning. PMLR, 24698--24724","author":"Xu Xiang","year":"2022","unstructured":"Xiang Xu, Karl DD Willis, Joseph G Lambourne, Chin-Yi Cheng, Pradeep Kumar Jayaraman, and Yasutaka Furukawa. 2022. SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks. In International Conference on Machine Learning. PMLR, 24698--24724."},{"key":"e_1_2_2_57_1","volume-title":"Ali Mahdavi Amiri, and Hao Zhang","author":"Yu Fenggen","year":"2023","unstructured":"Fenggen Yu, Qimin Chen, Maham Tanveer, Ali Mahdavi Amiri, and Hao Zhang. 2023. DualCSG: Learning Dual CSG Trees for General and Compact CAD Modeling. arXiv preprint arXiv:2301.11497 (2023)."},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01147"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/200"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658129","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:54Z","timestamp":1750291554000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,19]]},"references-count":59,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7,19]]}},"alternative-id":["10.1145\/3658129"],"URL":"https:\/\/doi.org\/10.1145\/3658129","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,19]]},"assertion":[{"value":"2024-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}