Spatial Interpretation in a text-to-image accelerated architectural design process: investigating diffusion models in sketch, preliminary and final design stages.

Vissers-Similon, Elien; Dounas, Theodoros

Abstract

The introduction of diffusion models – artificial intelligence models originally used as text-to-image generators – poses several questions for the architectural design process. Firstly, could diffusion models enhance those design processes? Secondly, what is the relationship between innovative image generators and traditional methods of representation derived from projectional geometry? This paper studies the results of such an accelerated design process by 76 masters students of architecture, which lasted 6 weeks and covered the sketch, preliminary and final design stages. We define spatial interpretation moments as the inflection points the during human-machine interaction when the designer translates 2D images into 3D spatial design concepts. The spatial interpretation moments mostly occur in the transition from sketch to preliminary design and during preliminary design. Spatial interpretation moments’ inherent opportunity is to use diffusion models both as a communication and a design tool to rapidly test spatial design intentions. This paper showcases examples of the captured spatial interpretation moments regarding the designer’s ability to actively design and the impact of spatial dimensions, spatial composition and spatial abstraction. Moreover, this paper suggests the use of annotations to capture spatial interpretation moments for future research and proposes boundaries to investigate the relationship between diffusion models and other methods of representation.

Citation

VISSERS-SIMILON, E. and DOUNAS, T. 2024. Spatial interpretation in a text-to-image accelerated architectural design process. In Kontovourkis, O., Phocas, M.C. and WURZER, G. (eds.) Proceedings of the 42nd International conference on education and research in computer aided architectural design in Europe 2024 (eCAADe 2024): data-driven intelligence, 9-13 September 2024, Nicosia, Cyprus. Brussels: eCAADe [online], 2, pages 527-536. Available from: https://doi.org/10.52842/conf.ecaade.2024.2.527

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 42nd International conference on education and research in computer aided architectural design in Europe 2024 (eCAADe 2024): data-driven intelligence
• Start Date: Sep 9, 2024
• End Date: Sep 13, 2024
• Acceptance Date: May 15, 2024
• Online Publication Date: Nov 17, 2024
• Publication Date: Jan 1, 2024
• Deposit Date: Jan 14, 2025
• Publicly Available Date: Jan 14, 2025
• Publisher: Education and Research in Computer Aided Architectural Design in Europe (eCAADe)
• Peer Reviewed: Peer Reviewed
• Volume: 2
• Pages: 527-536
• Series Title: eCAADe proceedings
• Series ISSN: 2684-1843
• ISBN: 9789491207389
• DOI: https://doi.org/10.52842/conf.ecaade.2024.2.527
• Keywords: Diffusion models; Midjourney; Enhanced design process; Human-machine interaction; Generative design
• Public URL: https://rgu-repository.worktribe.com/output/2613952