Generative Isovist Transformer: Machine learning for spatial sequence synthesis

Mikhael Johanes, Jeffrey Huang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

While isovists have been used widely to quantify and analyze architectural space, its utilization for generative design still needs to be explored. On the other hand, advanced deep learning has shown opportunities for data-driven generative design. This research revisits the isovist capacity to represent architecture as a series of spatial sequences and extends the role of isovists beyond merely a perception model to projective agents. This paper presents the development of GIsT: Generative Isovists Transformer in sampling, learning, and generating architectural spatial sequences. By coupling isovists with discrete representation and generative deep learning models, we untapped the generative potential of isovist representation for spatial sequence synthesis. We demonstrated its capacity to learn the architectural spatial sequence and extendability via few-shots learning. The results show a promising direction toward integrating data-driven experiential spatial synthesis in future computational design tools.

Original languageEnglish
Title of host publicationeCAADe 2023 - Digital Design Reconsidered
EditorsWolfgang Dokonal, Urs Hirschberg, Gabriel Wurzer, Gabriel Wurzer
PublisherEducation and research in Computer Aided Architectural Design in Europe
Pages471-480
Number of pages10
ISBN (Print)9789491207358
Publication statusPublished - 2023
Event41st Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2023 - Graz, Austria
Duration: 20 Sept 202322 Sept 2023

Publication series

NameProceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe
Volume2
ISSN (Print)2684-1843

Conference

Conference41st Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2023
Country/TerritoryAustria
CityGraz
Period20/09/2322/09/23

Keywords

  • Discrete Representation Learning
  • Generative Design
  • Isovist
  • Machine Learning
  • Spatial Sequence
  • Transformers

Fingerprint

Dive into the research topics of 'Generative Isovist Transformer: Machine learning for spatial sequence synthesis'. Together they form a unique fingerprint.

Cite this