The ‘AI Sampling Singapore’ (or ‘3D-GAN-Housing’) project by Assistant Professor Immanuel Koh has won the best Architectural Design – Speculative and Visionary award at the BLT Built Design Awards 2024.

Is it possible to sample at scale and at high-resolution every single building ever built in a country? If so, can such a dataset be used to train an AI model in generating new yet locally compliant buildings without any explicit regulatory control inputs?

The project explores the design agency of deep generative neural networks in learning architectural notions of three-dimensional exteriority and interiority with a redesigned 3D generative adversarial network (3D-GAN) architecture.

Trained with a large dataset of 3D digital models of high-rise buildings found in Singapore, it generates not only formally plausible and semantically coherent configurations but begins to also imagine novel and uncanny architectural forms, interpolating and extrapolating among standard high-rise housing typologies such as the slab and point blocks.

The work was previously on display at The Arts House and also exhibited at the 17th Venice Architecture Biennale’s CITYX Venice Italian Virtual Pavilion.

Assistant Prof Koh is affiliated with the Architecture and Sustainable Design (ASD) pillar and the Design and Artificial Intelligence (DAI) programme at SUTD. He directs Artificial-Architecture — an interdisciplinary research laboratory that focuses on the design and development of deep learning models for artificial creativity, generative architecture, predictive urbanism and defence intelligence.