Fluid Grey 2: How Well Does Generative Adversarial Network Learn Deeper Topology Structure in Architecture That Matches Images?

TL;DR

This paper demonstrates that pix2pix GAN can autonomously learn and recognize spatial topological relationships in architectural images, providing a quick, simple detection method that enhances design and urban renewal processes.

Contribution

It proves pix2pix's ability to learn topological relationships and introduces a novel, efficient detection method for assessing GAN performance from a topological perspective.

Findings

Pix2pix can automatically learn spatial topological relationships.

The proposed detection method is quick, simple, and effective.

Different input modes affect the learning efficiency of the GAN.

Abstract

Taking into account the regional characteristics of intrinsic and extrinsic properties of space is an essential issue in architectural design and urban renewal, which is often achieved step by step using image and graph-based GANs. However, each model nesting and data conversion may cause information loss, and it is necessary to streamline the tools to facilitate architects and users to participate in the design. Therefore, this study hopes to prove that I2I GAN also has the potential to recognize topological relationships autonomously. Therefore, this research proposes a method for quickly detecting the ability of pix2pix to learn topological relationships, which is achieved by adding two Grasshopper-based detection modules before and after GAN. At the same time, quantitative data is provided and its learning process is visualized, and changes in different input modes such as greyscale and RGB affect its learning efficiency. There are two innovations in this paper: 1) It proves that pix2pix can automatically learn spatial topological relationships and apply them to architectural design. 2) It fills the gap in detecting the performance of Image-based Generation GAN from a topological perspective. Moreover, the detection method proposed in this study takes a short time and is simple to operate. The two detection modules can be widely used for customizing image datasets with the same topological structure and for batch detection of topological relationships of images. In the future, this paper may provide a theoretical foundation and data support for the application of architectural design and urban renewal that use GAN to preserve spatial topological characteristics.