<div class="csl-bib-body">
<div class="csl-entry">Sebestyen, A., Özdenizci, O., Hirschberg, U., & Legenstein, R. (2023). Generating Conceptual Architectural 3D Geometries with Denoising Diffusion Models. In W. Dokonal, U. Hirschberg, & G. Wurzer (Eds.), <i>Proceedings of the 41st International Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe) [Volume 2]</i> (pp. 451–460). eCAADe. https://doi.org/10.52842/conf.ecaade.2023.2.451</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/192637
-
dc.description.abstract
Generative deep learning diffusion models have been attracting mainstream attention in the field of 2D image generation. We propose a prototype which brings a diffusion network into the third dimension, with the purpose of generating geometries for conceptual design. We explore the possibilities of generating 3D datasets, using parametric design to overcome the problem of the current lack of available architectural 3D data suitable for training neural networks. Furthermore, we propose a data representation based on volumetric density grids which is applicable to train diffusion networks. Our early prototype demonstrates the viability of the approach and suggests future options to develop deep learning generative 3D tools for architectural design.
en
dc.language.iso
en
-
dc.relation.ispartofseries
Proceedings of the 41st International Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe) [Volume 2]
-
dc.subject
3D Data Representations
en
dc.subject
Artificial Intelligence
en
dc.subject
Diffusion Models
en
dc.subject
Generative Deep Learning
en
dc.subject
Neural Networks
en
dc.subject
Parametric Design
en
dc.title
Generating Conceptual Architectural 3D Geometries with Denoising Diffusion Models
en
dc.type
Inproceedings
en
dc.type
Konferenzbeitrag
de
dc.relation.publication
Proceedings of the 41st International Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe) [Volume 2]
-
dc.contributor.affiliation
TU Graz - Institut für Grundlagen der Informationsverarbeitung
-
dc.contributor.affiliation
TU Graz - Institut für Grundlagen der Informationsverarbeitung
-
dc.contributor.editoraffiliation
Technische Universität Graz, Österreich
-
dc.contributor.editoraffiliation
Technische Universität Graz, Österreich
-
dc.relation.isbn
978-9-49120-735-8
-
dc.relation.issn
2684-1843
-
dc.description.startpage
451
-
dc.description.endpage
460
-
dc.type.category
Full-Paper Contribution
-
tuw.booktitle
Proceedings of the 41st International Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe) [Volume 2]
-
tuw.container.volume
2
-
tuw.relation.publisher
eCAADe
-
tuw.researchTopic.id
A1
-
tuw.researchTopic.name
Development and Advancement of the Architectural Arts
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E259-01 - Forschungsbereich Digitale Architektur und Raumplanung
-
tuw.publisher.doi
10.52842/conf.ecaade.2023.2.451
-
dc.description.numberOfPages
10
-
tuw.event.name
41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023)
en
tuw.event.startdate
20-09-2023
-
tuw.event.enddate
22-09-2023
-
tuw.event.online
Hybrid
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
Graz
-
tuw.event.country
AT
-
tuw.event.institution
Technische Universität Graz
-
tuw.event.presenter
Sebestyen, Adam
-
tuw.event.track
Multi Track
-
wb.sciencebranch
Architektur
-
wb.sciencebranch.oefos
2012
-
wb.sciencebranch.value
100
-
item.languageiso639-1
en
-
item.openairecristype
http://purl.org/coar/resource_type/c_5794
-
item.openairetype
conference paper
-
item.cerifentitytype
Publications
-
item.fulltext
no Fulltext
-
item.grantfulltext
none
-
crisitem.author.dept
E259 - Institut für Architekturwissenschaften
-
crisitem.author.dept
TU Graz - Institut für Grundlagen der Informationsverarbeitung
-
crisitem.author.dept
TU Graz - Institut für Grundlagen der Informationsverarbeitung