Design across multi-scale datasets by developing a novel approach to 3DGANs

Abstract

The development of Generative Adversarial Networks (GANs) has accelerated the research of Artificial Intelligence (AI) in architecture as a generative tool. However, since their initial invention, many versions have been developed that only focus on 2D image datasets for training and images as output. The current state of 3DGAN research has yielded promising results. However, these contributions focus primarily on building mass, extrusion of 2D plans, or the overall shape of objects. In comparison, our newly developed 3DGAN approach, using fully spatial building datasets, demonstrates that unprecedented interconnections across different scales are possible resulting in unconventional spatial configurations. Unlike a traditional design process, based on analyzing only a few precedents (typology) according to the task, by collaborating with the machine we can draw on a significantly wider variety of buildings across multiple typologies. In addition, the dataset was extended beyond the scale of complete buildings and involved building components that define space. Thus, our results achieve a high spatial diversity. A detailed analysis of the results also revealed new hybrid architectural elements illustrating that the machine continued the interconnections of scale since elements were not explicitly part of the dataset, becoming a true design collaborator.

From Linear to Manifold Interpolation: Exemplifying the paradigm shift through interpolation

“…Within the 2D case study, we employ different generative adversarial networks such as DCGAN and StyleGAN. While the use of 3DGANs in architecture is limited, we have developed a unique workflow to serve our specific purposes, which we elaborate on in a separate publication (Ennemoser and Mayrhofer-Hufnagl, 2023).…”