男人藏精阁

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 on display at Gallery 2 of the Old Parliament House in the exhibition 鈥淓YE RISE: Urbanscapes Between Human and Machine鈥�, itself commissioned by The Arts House and supported by the National Arts Council in Singapore. It features the outputs as 3D-printed architectural pieces (at the scales of 1:100 and 1:300), 3D latent walk video animations (in large screen formats), and full-height digital prints on paper (at super high resolution). The work was previously exhibited as the 鈥楢I Sampling Singapore鈥� project at the 17th Venice Architecture Biennale鈥檚 CITYX Venice Italian Virtual Pavilion.