{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T18:18:34Z","timestamp":1780424314798,"version":"3.54.1"},"reference-count":45,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12472117)"],"award-info":[{"award-number":["12472117)"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Peacock Program for Overseas High-Level Talents Introduction of Shenzhen City","award":["KQTD20200820113110016"],"award-info":[{"award-number":["KQTD20200820113110016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Direct B-Rep generation is increasingly important in Computer-Aided Design (CAD) workflows, eliminating costly modeling sequence data and enabling the creation of complex features. A key challenge is modeling the joint distribution of the misaligned geometry and topology. Existing methods tend to implicitly embed topology into the geometric features of edges. Although this integration ensures feature alignment, it also causes edge geometry to carry more redundant structural information compared to the original B-Rep, leading to significantly higher computational cost. For efficient generation, GraphBRep, a B-Rep generation model that explicitly represents and learns compact topology, is proposed. Based on the original B-Rep structure, an undirected weighted graph is constructed to represent the surface topology. A graph diffusion model is employed to learn topology conditioned on surface features, serving as the basis for determining connectivity between primitive surfaces. The explicit representation ensures a compact data structure, effectively reducing computational cost during both training and inference. Experiments on two large-scale unconditional datasets and one category-conditional dataset demonstrate that the proposed method significantly reduces training and inference times (up to 30.82% and 56.3% for given datasets, respectively) while maintaining high-quality CAD generation compared with SOTA.<\/jats:p>","DOI":"10.1093\/jcde\/qwaf136","type":"journal-article","created":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T12:30:38Z","timestamp":1765801838000},"page":"259-274","source":"Crossref","is-referenced-by-count":1,"title":["<i>GraphBRep<\/i>\n                    : Explicit Graph Diffusion of B\u2013Rep Topology for Efficient CAD Generation"],"prefix":"10.1093","volume":"13","author":[{"given":"Weilin","family":"Lai","sequence":"first","affiliation":[{"name":"State Key Laboratory of Advanced Design and Manufacturing for Vehicle, Hunan University , Changsha 410082 ,","place":["PR China"]},{"name":"Beijing Institute of Technology Shenzhen Automotive Research Institute , Shenzhen 518000 ,","place":["PR China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tie","family":"Xu","sequence":"additional","affiliation":[{"name":"SAIC GM Wuling Automobile Co., Ltd , Liuzhou 545007 ,","place":["PR China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Niu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Design and Manufacturing for Vehicle, Hunan University , Changsha 410082 ,","place":["PR China"]},{"name":"Beijing Institute of Technology Shenzhen Automotive Research Institute , Shenzhen 518000 ,","place":["PR China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5974-4499","authenticated-orcid":false,"given":"Hu","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Design and Manufacturing for Vehicle, Hunan University , Changsha 410082 ,","place":["PR China"]},{"name":"Beijing Institute of Technology Shenzhen Automotive Research Institute , Shenzhen 518000 ,","place":["PR China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,12,16]]},"reference":[{"key":"2026050910320038400_bib2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.2311.15127","article-title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"2026050910320038400_bib3","doi-asserted-by":"publisher","first-page":"5881","DOI":"10.1109\/CVPR52734.2025.00552","article-title":"PartGen: Part-level 3D generation and reconstruction with multi-view diffusion models","author":"Chen","year":"2025","journal-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"2026050910320038400_bib4","first-page":"1","article-title":"NVDiff: Graph generation through the diffusion of node vectors","author":"Chen","year":"2023","journal-title":"arXiv:2211.10794"},{"key":"2026050910320038400_bib6","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1093\/jcde\/qwaf091","article-title":"Automatic reconstruction of 3D topology optimization to editable CAD model with rotation minimizing frames","volume":"12","author":"Feng","year":"2025","journal-title":"Journal of Computational Design and Engineering"},{"key":"2026050910320038400_bib7","first-page":"5885","article-title":"Computer-aided design as language","volume":"34","author":"Ganin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026050910320038400_bib8","first-page":"5885","article-title":"Computer-aided design as language","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Ganin","year":"2024"},{"key":"2026050910320038400_doi46_874_283125","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"key":"2026050910320038400_bib9","doi-asserted-by":"publisher","first-page":"129:1","DOI":"10.1145\/3528223.3530078","article-title":"ComplexGen: CAD reconstruction by B-rep chain complex generation","volume":"41","author":"Guo","year":"2022","journal-title":"ACM transactions on graphics"},{"key":"2026050910320038400_bib10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026050910320038400_bib11","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1109\/ICDM54844.2022.00030","article-title":"GraphGDP: Generative diffusion processes for permutation invariant graph generation","author":"Huang","year":"2022"},{"key":"2026050910320038400_bib12","article-title":"SolidGen: An autoregressive model for direct B-rep synthesis","author":"Jayaraman","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"2026050910320038400_bib13","doi-asserted-by":"crossref","first-page":"11698","DOI":"10.1109\/CVPR46437.2021.01153","article-title":"UV-Net: Learning from boundary representations","author":"Jayaraman","year":"2021","journal-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"2026050910320038400_bib14","first-page":"10362","article-title":"Score-based generative modeling of graphs via the system of stochastic differential equations","volume":"162","author":"Jo","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning"},{"key":"2026050910320038400_bib15","article-title":"Auto-Encoding Variational Bayes","author":"Kingma","year":"2022","journal-title":"In Proceedings of the International Conference on Learning Representations (ICLR) 2014"},{"key":"2026050910320038400_bib16","doi-asserted-by":"crossref","first-page":"9593","DOI":"10.1109\/CVPR.2019.00983","article-title":"ABC: A big CAD model dataset for geometric deep learning","author":"Koch","year":"2019","journal-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"2026050910320038400_bib17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.03603","article-title":"HunyuanVideo: A systematic framework for large video generative models","author":"Kong","year":"2025","journal-title":"arXiv:2412.03603"},{"key":"2026050910320038400_bib18","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1093\/jcde\/qwaf102","article-title":"CADCL: Reconstruct parametric CAD models from B-rep via contrastive learning","volume":"12","author":"Liang","year":"2025","journal-title":"Journal of Computational Design and Engineering"},{"key":"2026050910320038400_bib19","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.1145\/3563657.3596098","article-title":"3DALL-E: Integrating text-to-image ai in 3d design workflows","author":"Liu","year":"2023","journal-title":"Proceedings of the 2023 ACM Designing Interactive Systems Conference"},{"key":"2026050910320038400_bib20","doi-asserted-by":"publisher","first-page":"27144","DOI":"10.1109\/CVPR52733.2024.02564","article-title":"Draw step by step: Reconstructing CAD construction sequences from point clouds via multimodal diffusion","volume-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Ma","year":"2024"},{"key":"2026050910320038400_bib21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.15279","article-title":"Don\u2019t mesh with me: Generating constructive solid geometry instead of meshes by fine-tuning a code-generation LLM","author":"Mews","year":"2024","journal-title":"arXiv:2411.15279"},{"key":"2026050910320038400_doi47_543_285925","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","article-title":"NeRF","volume":"65","author":"Mildenhall","year":"2021","journal-title":"Communications of the ACM"},{"key":"2026050910320038400_bib23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.08751","article-title":"Point-E: A system for generating 3D point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv:2212.08751"},{"key":"2026050910320038400_bib24","first-page":"4474","article-title":"Permutation invariant graph generation via score-based generative modeling","author":"Niu","year":"2020","journal-title":"Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics"},{"key":"2026050910320038400_bib1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.08774","article-title":"GPT-4 technical report","author":"OpenAI","year":"2024","journal-title":"arXiv:2303.08774"},{"key":"2026050910320038400_bib25","first-page":"5077","article-title":"SketchGen: Generating constrained CAD sketches","volume":"34","author":"Para","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026050910320038400_bib26","doi-asserted-by":"publisher","first-page":"4172","DOI":"10.1109\/ICCV51070.2023.00387","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2023","journal-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"2026050910320038400_bib27","first-page":"1862","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume":"2024","author":"Podell","year":"2023","journal-title":"International Conference on Representation Learning"},{"key":"2026050910320038400_bib28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.13720","article-title":"Movie Gen: A cast of media foundation models","author":"Polyak","year":"2025","journal-title":"arXiv:2410.13720"},{"key":"2026050910320038400_bib29","article-title":"DreamFusion: Text-to-3D using 2D diffusion","author":"Poole","year":"2023","journal-title":"The Eleventh International Conference on Learning Representations"},{"key":"2026050910320038400_bib30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.15115","article-title":"Qwen2.5 technical report","author":"Qwen,\u00a0Yang","year":"2025","journal-title":"arXiv:2412.15115"},{"key":"2026050910320038400_bib31","first-page":"8821","article-title":"Zero-Shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"2026050910320038400_bib32","doi-asserted-by":"publisher","first-page":"10684","DOI":"10.1109\/CVPR52688.2022.01042","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"2026050910320038400_bib33","doi-asserted-by":"publisher","first-page":"10674","DOI":"10.1109\/CVPR52688.2022.01042","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"2026050910320038400_bib34","article-title":"Vitruvion: A generative model of parametric CAD sketches","author":"Seff","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"2026050910320038400_bib35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.13971","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"2026050910320038400_bib36","article-title":"DiGress: Discrete denoising diffusion for graph generation","author":"Vignac","year":"2023","journal-title":"The Eleventh International Conference on Learning Representations"},{"key":"2026050910320038400_bib37","article-title":"Diffusers: State-of-the-art diffusion models (Version 0.12.1) [Python]","author":"von\u00a0Platen","year":"2025"},{"key":"2026050910320038400_bib38","doi-asserted-by":"publisher","first-page":"6752","DOI":"10.1109\/ICCV48922.2021.00670","article-title":"DeepCAD: A deep generative network for computer-aided design models","author":"Wu","year":"2021","journal-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"2026050910320038400_bib39","first-page":"38443","article-title":"Hierarchical neural coding for controllable CAD model generation","volume":"202","author":"Xu","year":"2023","journal-title":"In Proceedings of the 40th International Conference on Machine Learning (ICML'23)"},{"key":"2026050910320038400_bib40","doi-asserted-by":"publisher","DOI":"10.1145\/3658129","article-title":"BrepGen: A B-rep generative diffusion model with structured latent geometry","volume":"43","author":"Xu","year":"2024","journal-title":"ACM Trans. Graph."},{"key":"2026050910320038400_bib41","first-page":"24698","article-title":"SkexGen: Autoregressive generation of cad construction sequences with disentangled codebooks","volume":"162","author":"Xu","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning"},{"key":"2026050910320038400_bib42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.06206","article-title":"Text2CAD: Text to 3D CAD generation via technical drawings","author":"Yavartanoo","year":"2024","journal-title":"arXiv:2411.06206"},{"key":"2026050910320038400_bib43","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1093\/jcde\/qwae005","article-title":"Brep2Seq: A dataset and hierarchical deep learning network for reconstruction and generation of computer-aided design models","volume":"11","author":"Zhang","year":"2024","journal-title":"Journal of Computational Design and Engineering"},{"key":"2026050910320038400_bib44","article-title":"FlexCAD: Unified and versatile controllable CAD generation with fine-tuned large language models","author":"Zhang","year":"2025","journal-title":"The Thirteenth International Conference on Learning Representations"},{"key":"2026050910320038400_bib45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.12202","article-title":"Hunyuan3D 2.0: Scaling diffusion models for high resolution textured 3d assets generation","author":"Zhao","year":"2025","journal-title":"arXiv:2501.12202"}],"container-title":["Journal of Computational Design and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcde\/advance-article-pdf\/doi\/10.1093\/jcde\/qwaf136\/65912617\/qwaf136.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/13\/1\/259\/65912617\/qwaf136.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/13\/1\/259\/65912617\/qwaf136.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T14:32:13Z","timestamp":1778337133000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/13\/1\/259\/8381229"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,16]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,2]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwaf136","relation":{},"ISSN":["2288-5048"],"issn-type":[{"value":"2288-5048","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1]]},"published":{"date-parts":[[2025,12,16]]}}}