Many of the tools used by architects to design, conceptualize and experiment have entered into the discipline from fields such as engineering, manufacturing or animation. As a result, values such as optimization, standardization and efficiency have discretely found their way into these tools and have greatly informed and constrained the possible design space. In this paper, we target the need to integrate lateral thinking strategies in digital design tools. Within this context, we propose a methodology that uses GANs and their properties as an experimentation ground to reevaluate the lateral thinking constraints in architectural tools. Specifically, we use StyleGAN and explore the ability to access its latent space as part of an architectural design process. The presented methodology constitutes a 4-step approach that draws from the abilities and properties of this space to design architecture: initializing the virtual environment of points (through training), entering the space (randomly or with an intent), moving through space (through arithmetic operations and interpolations), and finally generating a voxelized 3D form from interpolated images. By doing this, and through a demonstrated case study, we show how this series of techniques could result in unexpected spaces, resulting in creative output beyond what is produced by human capability alone.
In accordance with The New School's Intellectual Property Rights Policy, copyright is held by each thesis' respective author. The responsibility to secure copyright permission rests with the user.; http://rightsstatements.org/vocab/InC/1.0/
There’s more! What you see on this site is only what is viewable online. Please visit archives.newschool.edu to find out more about what’s in the archives.