The Ar-chair-tecture project is an exploration of architectural interiority and exteriority using 3D generative adversarial networks (GANs) to produce spatial and formal prompts for creative computational 3D designs across scales and domains. In recent years, with the readily available dataset of natural images and the relative ease of preparing curated datasets of 2D designs, many designers have begun to experiment with GANs in producing novel and inspirational-looking 2D imagery. While some designers have tried to intuitively interpret them as 3D forms indirectly, the project argues that a direct computational translation from 3D-GAN generated forms to 3D physical artefacts suggests significant design potential for creative spatial ideation, complex formal experimentation, integrated digital fabrication and reconfigurable construction assembly logic. Perhaps, even engendering a new deep learning-based architectural and sculptural aesthetics. Two datasets of voxel models were created, one with 4000 chairs and the other with 4000 residential building blocks. Their contrast in scale is deliberate in order to show that 3D visual-spatial prompts need not be domain specific, and could even be meaningfully sampled and interpolated given a shared latent space.
