Exploration of three-dimensional spatial learning approach based on machine learning–taking Taihu stone as an example

Abstract

Under the influence of globalization, the transformation of traditional architectural space is vital to the growth of local architecture. As an important spatial element of traditional gardens, Taihu stone has the image qualities of being “thin, wrinkled, leaky and transparent” The “transparency” and “ leaky” of Taihu stone reflect the connectivity and irregularity of Taihu stone’s holes, which are consistent with the contemporary architectural design concepts of fluid space and transparency. Nonetheless, relatively few theoretical studies have been conducted on the spatial analysis and design transformation of Taihu stone. Using machine learning, we attempt to extract the three-dimensional spatial variation pattern of Taihu stone in this paper. This study extracts 3D spatial features for experiments using artificial neural networks (ANN) and generative adversarial networks (GAN). In order to extract 3D spatial variation patterns, the machine learning model learns the variation patterns between adjacent sections. The trained machine learning model is capable of generating a series of spatial sections with the spatial variation pattern of the Taihu stone. The purpose of the experimental results is to compare the performance of various machine learning models for 3D space learning in order to identify a model with superior performance. This paper also presents a novel concept for machine learning to master continuous 3D spatial features.