Utilizing Generative Adversarial Networks for Augmenting Architectural Massing Studies: AI-assisted Mixed Reality

Abstract

A technique for architectural massing studies in Mixed Reality (MR) is described. Generative Adversarial Networks let an object appear to have a different material than it actually has. The benefits during design are twofold. From one side the congruence between shape and material are subject to verification in real-time. From the other side, the designer is liberated from the usual restrictions and biases as to shape that are inevitable due to the mechanical properties of a mock-up. This is referred to as artificial intelligence assisted MR (AI-A MR) in this work. The technique consists of two steps: Based on preparing synthetic data in Rhino/Grasshopper to be trained with an image-to-image translation model and implemented to the trained model in MR design environment. Next to the practical merits, a contribution of the work with respect to MR methodology is that it exemplifies the solution of some persistent tracking and registration problems.