Brep2Seq: A dataset and hierarchical deep learning network for reconstruction and generation of computer-aided design models

IF 5.4 3区 材料科学 Q2 CHEMISTRY, PHYSICAL
Shuming Zhang, Zhidong Guan, Hao Jiang, Tao Ning, Xiaodong Wang, Pingan Tan
{"title":"Brep2Seq: A dataset and hierarchical deep learning network for reconstruction and generation of computer-aided design models","authors":"Shuming Zhang, Zhidong Guan, Hao Jiang, Tao Ning, Xiaodong Wang, Pingan Tan","doi":"10.1093/jcde/qwae005","DOIUrl":null,"url":null,"abstract":"\n 3D reconstruction is a significant research topic in the field of Computer-Aided Design (CAD), which is used to recover editable CAD models from original shapes, including point clouds, voxels, meshes, and boundary representations (B-rep). Recently, there has been considerable research interest in deep model generation due to the increasing potential of deep learning methods. To address the challenges of 3D reconstruction and generation, we propose Brep2Seq, a novel deep neural network designed to transform the B-rep model into a sequence of editable parametrized feature-based modeling operations comprising principal primitives and detailed features. Brep2Seq employs an encoder-decoder architecture based on the Transformer, leveraging geometry and topological information within B-rep models to extract the feature representation of the original 3D shape. Due to its hierarchical network architecture and training strategy, Brep2Seq achieved improved model reconstruction and controllable model generation by distinguishing between the primary shape and detailed features of CAD models. To train Brep2Seq, a large-scale dataset comprising one million CAD designs is established through an automatic geometry synthesis method. Extensive experiments on both DeepCAD and Fusion 360 datasets demonstrate the effectiveness of Brep2Seq, and show its applicability to simple mechanical components in real-world scenarios. We further apply Brep2Seq to various downstream applications, including point cloud reconstruction, model interpolation, shape constraint generation and CAD feature recognition.","PeriodicalId":4,"journal":{"name":"ACS Applied Energy Materials","volume":"24 5","pages":""},"PeriodicalIF":5.4000,"publicationDate":"2024-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Energy Materials","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1093/jcde/qwae005","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

Abstract

3D reconstruction is a significant research topic in the field of Computer-Aided Design (CAD), which is used to recover editable CAD models from original shapes, including point clouds, voxels, meshes, and boundary representations (B-rep). Recently, there has been considerable research interest in deep model generation due to the increasing potential of deep learning methods. To address the challenges of 3D reconstruction and generation, we propose Brep2Seq, a novel deep neural network designed to transform the B-rep model into a sequence of editable parametrized feature-based modeling operations comprising principal primitives and detailed features. Brep2Seq employs an encoder-decoder architecture based on the Transformer, leveraging geometry and topological information within B-rep models to extract the feature representation of the original 3D shape. Due to its hierarchical network architecture and training strategy, Brep2Seq achieved improved model reconstruction and controllable model generation by distinguishing between the primary shape and detailed features of CAD models. To train Brep2Seq, a large-scale dataset comprising one million CAD designs is established through an automatic geometry synthesis method. Extensive experiments on both DeepCAD and Fusion 360 datasets demonstrate the effectiveness of Brep2Seq, and show its applicability to simple mechanical components in real-world scenarios. We further apply Brep2Seq to various downstream applications, including point cloud reconstruction, model interpolation, shape constraint generation and CAD feature recognition.
Brep2Seq:用于重建和生成计算机辅助设计模型的数据集和分层深度学习网络
三维重建是计算机辅助设计(CAD)领域的一个重要研究课题,用于从原始形状(包括点云、体素、网格和边界表示(B-rep))中恢复可编辑的 CAD 模型。最近,由于深度学习方法的潜力越来越大,人们对深度模型生成产生了浓厚的研究兴趣。为了应对三维重建和生成的挑战,我们提出了 Brep2Seq,这是一种新颖的深度神经网络,旨在将 B-rep 模型转化为一连串可编辑的基于特征的参数化建模操作,其中包括主基元和细节特征。Brep2Seq 采用基于变换器的编码器-解码器架构,利用 B-rep 模型中的几何和拓扑信息来提取原始三维形状的特征表示。由于采用了分层网络架构和训练策略,Brep2Seq 通过区分 CAD 模型的主要形状和细节特征,实现了更好的模型重建和可控模型生成。为了训练 Brep2Seq,我们通过自动几何合成方法建立了一个包含一百万个 CAD 设计的大规模数据集。在 DeepCAD 和 Fusion 360 数据集上进行的广泛实验证明了 Brep2Seq 的有效性,并展示了它在实际场景中对简单机械部件的适用性。我们进一步将 Brep2Seq 应用于各种下游应用,包括点云重建、模型插值、形状约束生成和 CAD 特征识别。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
ACS Applied Energy Materials
ACS Applied Energy Materials Materials Science-Materials Chemistry
CiteScore
10.30
自引率
6.20%
发文量
1368
期刊介绍: ACS Applied Energy Materials is an interdisciplinary journal publishing original research covering all aspects of materials, engineering, chemistry, physics and biology relevant to energy conversion and storage. The journal is devoted to reports of new and original experimental and theoretical research of an applied nature that integrate knowledge in the areas of materials, engineering, physics, bioscience, and chemistry into important energy applications.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信