综述：用于建筑设计的生成式人工智能

微信扫码，打开到小程序

Generative AI for Architectural Design: A Literature Review Chengyuan Li1 Tianyu Zhang2 Xusheng Du2 Ye Zhang1* Haoran Xie2 1Tianjin University 2Japan Advanced Institute of Science and Technology Abstract Generative Artificial Intelligence (AI) has pioneered new methodological paradigms in architectural design, signifi- cantly expanding the innovative potential and efficiency of the design process. This paper explores the extensive appli- cations of generative AI technologies in architectural de- sign, a trend that has benefitted from the rapid develop- ment of deep generative models. Generative Adversarial Networks (GANs) and Variational Autoencoder (VAE) have been extensively applied before, significantly advancing de- sign innovation and efficiency. With continual technolog- ical advancements, state-of-the-art Diffusion Models and 3D Generative Models are progressively integrated into ar- chitectural design, offering designers a more diversified set of creative tools and methodologies. This article further provides a comprehensive review of the basic principles of generative AI and large-scale models and highlights the applications in the generation of 2D images, videos, and 3D models. In addition, by reviewing the latest literature from 2020, this paper scrutinizes the impact of generative AI technologies at different stages of architectural design, from generating initial architectural 3D forms to produc- ing final architectural imagery. The marked trend of re- search growth indicates an increasing inclination within the architectural design community towards embracing gener- ative AI, thereby catalyzing a shared enthusiasm for re- search. These research cases and methodologies have not only proven to enhance efficiency and innovation signifi- cantly but have also posed challenges to the conventional boundaries of architectural creativity. Finally, we point out new directions for design innovation and articulate fresh trajectories for applying generative AI in the architectural domain. This article provides the first comprehensive liter- ature review about generative AI for architectural design, and we believe this work can facilitate more research work on this significant topic in architecture. Keywords: Generative AI, Architectural Design, Diffusion Models, 3D Generative Models, Large-scale models. *corresponding author, zhang.ye@tju.edu.cn Figure 1. Examples of architecture design using generative AI techniques: (a) church design [1]; (b) matrix of cuboid shapes [2]; (c) Frank Gehry’s Walt Disney concert hall [3]; (d) Bangkok urban design [4]; (e) foresting architecture [4]; (f) Urban interiors [4] and (g) text-to-architectural design [5]. 1. Introduction Nowadays, generative artificial intelligence (AI) tech- niques increasingly expand their power and revolution in ar- chitectural design. Here, generative AI refers to the artificial intelligence technologies dedicated to content generation, such as text, images, music, and videos. Generative AI ben- efits from the rapid development of deep generative models, including Generative Adversarial Networks (GANs), Vari- ational Autoencoder (VAE), and Diffusion Models (DMs). GANs and VAE are traditional generative models, and have been widely explored in architectural design, as illustrated in Figure 1. In this paper, we focus on the recent progress of generative AI, especially the revolutionary diffusion mod- els. DMs achieved state-of-the-art performance in various content generation tasks such as text-to-image and text-to- 3D-models. Architectural design may encompass multiple themes and scopes, with each project having distinct design re- quirements and individual styles, leading to diversity and complexity in design approaches. In this work, we adopt 6 main steps in the architectural design process for the lit- erature review: 1) architectural preliminary 3D forms de- 1 arXiv:2404.01335v1 [cs.LG] 30 Mar 2024 sign, 2) architectural layout design, 3) architectural struc- tural system design, 4) detailed and optimization design of architectural 3D forms, 5) architectural facade design, and 6) architectural imagery expression. After exploring the re- search papers from 2020 to 2023, we observed there has been a significant increase in the number of research papers in architectural design using Generative AI. The number of research papers using Generative AI technology in different architectural design steps reveals the development trends within each subfield, as illustrated in Figure 2(a). Most re- searches are concentrated in the area of architectural plan design. Research in preliminary 3D form design of archi- tecture and architectural image expression has rapidly in- creased in the past two years. More research needs to be done by scholars on architectural, structural system design, architectural 3D form refinement and optimization design, and architectural facade design. This sustained growth trend distinctly demonstrates that generative AI in architectural design are expanding at an un- precedented rate while also reflecting the architectural de- sign and computer science community have high level of attention and increasing investment in Generative AI tech- nologies. The most used generative AI techniques are illus- trated in Fig 2(b). In computer science, many studies focus on GAN and VAE, while research on DDPM, LDM, and GPT is in the initial stages. The situation is the same in architecture. 1.1. Motivation Leveraging the recent generative AI models in architec- tural design could significantly improve design efficiency, and provide architects with new design processes and ideas to expand the possibilities of architectural design and rev- olutionize the entire design process. However, the use of advanced generative models in architectural design has not been explored extensively. The primary reasons for hinder- ing the use of advanced generative models in architectural design may have two aspects: the professional barriers and the issue of training data. In terms of professional barriers, deep learning and ar- chitectural design are highly specialized fields requiring ex- tensive professional knowledge and experience. The aim of this study is to narrow the professional barriers between ar- chitecture and computer science, and assist architectural de- signers in bridging Generative AI technologies with appli- cations, promoting interdisciplinary research, and delineat- ing future research directions. This review systematically analyzes and summarizes case studies and research out- comes of Generative AI applications in architectural design, and showcases the possibilities and potential of the intersec- tion between computer science and architecture. This in- terdisciplinary perspective encourages collaboration among experts from different fields to address complex issues in architectural design, thus advancing scientific research and technological innovation. In terms of the issue of training data, deep learning mod- els require high-quality training data to analyze and ver- ify their generalization ability. However, data in the field of architecture is usually unstructured. The search and or- ganization of architectural training data pose a significant challenge, making it difficult right from the initial stages of model training. In addition, high-performance Graphics Processing Units (GPUs) are required to train the millions of data for deep learning models, especially those dealing with complex images and datasets. The scarcity of high- performance GPUs and the difficulty of mastering GPU pro- gramming skills may prevent the architects to explore the recent diffusion model and large foundation models. 1.2. Structure and Methodology This article first introduces the development and applica- tion directions of generative AI models, then elaborates on the methods of applying generative AI in the architectural design process, and finally, forecasts the potential applica- tion development of generative AI in the architectural field. In section 2, the article offers an in-depth introduction to the principles and evolution of various generative AI mod- els, wit