用深度变分自动编码器生成建筑类型的几何插值

IF 1.8 Q3 ENGINEERING, MANUFACTURING
Design Science Pub Date : 2020-12-28 DOI:10.1017/dsj.2020.31
Jaime de Miguel Rodríguez, M. Villafañe, Luka Piškorec, Fernando Sancho Caparrini
{"title":"用深度变分自动编码器生成建筑类型的几何插值","authors":"Jaime de Miguel Rodríguez, M. Villafañe, Luka Piškorec, Fernando Sancho Caparrini","doi":"10.1017/dsj.2020.31","DOIUrl":null,"url":null,"abstract":"Abstract This work presents a methodology for the generation of novel 3D objects resembling wireframes of building types. These result from the reconstruction of interpolated locations within the learnt distribution of variational autoencoders (VAEs), a deep generative machine learning model based on neural networks. The data set used features a scheme for geometry representation based on a ‘connectivity map’ that is especially suited to express the wireframe objects that compose it. Additionally, the input samples are generated through ‘parametric augmentation’, a strategy proposed in this study that creates coherent variations among data by enabling a set of parameters to alter representative features on a given building type. In the experiments that are described in this paper, more than 150 k input samples belonging to two building types have been processed during the training of a VAE model. The main contribution of this paper has been to explore parametric augmentation for the generation of large data sets of 3D geometries, showcasing its problems and limitations in the context of neural networks and VAEs. Results show that the generation of interpolated hybrid geometries is a challenging task. Despite the difficulty of the endeavour, promising advances are presented.","PeriodicalId":54146,"journal":{"name":"Design Science","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2020-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1017/dsj.2020.31","citationCount":"5","resultStr":"{\"title\":\"Generation of geometric interpolations of building types with deep variational autoencoders\",\"authors\":\"Jaime de Miguel Rodríguez, M. Villafañe, Luka Piškorec, Fernando Sancho Caparrini\",\"doi\":\"10.1017/dsj.2020.31\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract This work presents a methodology for the generation of novel 3D objects resembling wireframes of building types. These result from the reconstruction of interpolated locations within the learnt distribution of variational autoencoders (VAEs), a deep generative machine learning model based on neural networks. The data set used features a scheme for geometry representation based on a ‘connectivity map’ that is especially suited to express the wireframe objects that compose it. Additionally, the input samples are generated through ‘parametric augmentation’, a strategy proposed in this study that creates coherent variations among data by enabling a set of parameters to alter representative features on a given building type. In the experiments that are described in this paper, more than 150 k input samples belonging to two building types have been processed during the training of a VAE model. The main contribution of this paper has been to explore parametric augmentation for the generation of large data sets of 3D geometries, showcasing its problems and limitations in the context of neural networks and VAEs. Results show that the generation of interpolated hybrid geometries is a challenging task. Despite the difficulty of the endeavour, promising advances are presented.\",\"PeriodicalId\":54146,\"journal\":{\"name\":\"Design Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2020-12-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1017/dsj.2020.31\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Design Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1017/dsj.2020.31\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, MANUFACTURING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Design Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1017/dsj.2020.31","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MANUFACTURING","Score":null,"Total":0}
引用次数: 5

摘要

摘要这项工作提出了一种生成类似建筑类型线框的新型3D对象的方法。这些结果来自于变分自动编码器(VAE)的学习分布中的插值位置的重建,VAE是一种基于神经网络的深度生成机器学习模型。所使用的数据集具有基于“连接图”的几何图形表示方案,该方案特别适合于表示组成它的线框对象。此外,输入样本是通过“参数扩充”生成的,本研究中提出的一种策略,通过使一组参数能够改变给定建筑类型的代表性特征,在数据之间产生连贯的变化。在本文描述的实验中,在VAE模型的训练过程中,已经处理了属于两种建筑类型的超过150k个输入样本。本文的主要贡献是探索用于生成三维几何结构的大型数据集的参数扩充,展示了其在神经网络和VAE背景下的问题和局限性。结果表明,插值混合几何图形的生成是一项具有挑战性的任务。尽管这项努力很困难,但仍取得了有希望的进展。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Generation of geometric interpolations of building types with deep variational autoencoders
Abstract This work presents a methodology for the generation of novel 3D objects resembling wireframes of building types. These result from the reconstruction of interpolated locations within the learnt distribution of variational autoencoders (VAEs), a deep generative machine learning model based on neural networks. The data set used features a scheme for geometry representation based on a ‘connectivity map’ that is especially suited to express the wireframe objects that compose it. Additionally, the input samples are generated through ‘parametric augmentation’, a strategy proposed in this study that creates coherent variations among data by enabling a set of parameters to alter representative features on a given building type. In the experiments that are described in this paper, more than 150 k input samples belonging to two building types have been processed during the training of a VAE model. The main contribution of this paper has been to explore parametric augmentation for the generation of large data sets of 3D geometries, showcasing its problems and limitations in the context of neural networks and VAEs. Results show that the generation of interpolated hybrid geometries is a challenging task. Despite the difficulty of the endeavour, promising advances are presented.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Design Science
Design Science ENGINEERING, MANUFACTURING-
CiteScore
4.80
自引率
12.50%
发文量
19
审稿时长
22 weeks
×
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