AASH-2016-Deep

This gallery consists of samples taken from my design studio (Deep Urbanism) conducted at the 2016 (15–23 July) AA Shanghai Visiting School (Architectural Association School of Architecture, London). An 11-day long summer workshop held at the HKU Shanghai Centre. A series of experiments was carried out to investigate the deep learning techniques of neural style transfer at the scale and in the context of architecture and urbanism. 

Neural Style Transfer (Facades):

Neural Style Transfer (Urban Plans):

Sampling of Shanghai’s Puxi as the urban structure/‘content’ and Pudong as the urban fabric/‘texture’, and vice versa. The neural style transfer (without semantic maps) was implemented using Tensorflow in 2016.

Neural Style Transfer (Floor Plans):

Sampling of 2 different office building floor plans from Shanghai’s Puxi and Pudong as structure/‘content’ and fabric/‘texture’, and vice versa. The neural style transfer (without semantic maps) was implemented using Tensorflow in 2016.