Generation of geometric interpolations of building types with deep variational autoencoders

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorde Miguel, Jaimeen_US
dc.contributor.authorEugenia Villafane, Mariaen_US
dc.contributor.authorPiškorec, Lukaen_US
dc.contributor.authorSancho-Caparrini, Fernandoen_US
dc.contributor.departmentDepartment of Architectureen
dc.contributor.organizationUniversity of Sevilleen_US
dc.contributor.organizationImperial College Londonen_US
dc.date.accessioned2021-01-25T10:09:48Z
dc.date.available2021-01-25T10:09:48Z
dc.date.issued2020-12-28en_US
dc.description.abstractThis 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 endeavor, promising advances are presented.en
dc.description.versionPeer revieweden
dc.format.extent35
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationde Miguel, J, Eugenia Villafane, M, Piškorec, L & Sancho-Caparrini, F 2020, ' Generation of geometric interpolations of building types with deep variational autoencoders ', Design Science, vol. 6, no. e34, 34 . https://doi.org/10.1017/dsj.2020.31en
dc.identifier.doi10.1017/dsj.2020.31en_US
dc.identifier.issn2053-4701
dc.identifier.otherPURE UUID: 30cce595-72e2-4e00-a090-dfc264f3a521en_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/30cce595-72e2-4e00-a090-dfc264f3a521en_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85098333540&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/54870027/generation_of_geometric_interpolations_of_building_types_with_deep_variational_autoencoders.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/102113
dc.identifier.urnURN:NBN:fi:aalto-202101251423
dc.language.isoenen
dc.publisherCambridge University Press
dc.relation.ispartofseriesDesign Scienceen
dc.relation.ispartofseriesVolume 6, issue e34en
dc.rightsopenAccessen
dc.titleGeneration of geometric interpolations of building types with deep variational autoencodersen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionpublishedVersion

Files