Computer-Aided Layout Generation for Building Design: A Review

2025-04-13

AI Summary

This paper addresses key bottlenecks in automated architectural layout generation—namely, heavy reliance on manual post-processing, low efficiency, and poor scalability. Methodologically, it systematically surveys three core directions: floorplan generation, scene layout synthesis, and multi-format layout generation; unifies problem definitions, input constraint paradigms, and evaluation metrics; and proposes the first machine learning–driven cross-method comparative framework integrating optimization algorithms, heuristic rules, and deep generative models (GANs, VAEs, diffusion models), enhanced with multimodal conditional modeling and structured representations. It introduces a domain-specific knowledge graph to quantitatively assess state-of-the-art methods across semantic plausibility, layout quality, and human-AI collaboration. As a key contribution, the authors release *awesome-building-layout-generation*, an open-source resource repository. This work establishes the first systematic, reproducible benchmark and reference framework for AI-powered intelligent architectural design.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Generating realistic building layouts for automatic building design has been studied in both the computer vision and architecture domains. Traditional approaches from the architecture domain, which are based on optimization techniques or heuristic design guidelines, can synthesize desirable layouts, but usually require post-processing and involve human interaction in the design pipeline, making them costly and timeconsuming. The advent of deep generative models has significantly improved the fidelity and diversity of the generated architecture layouts, reducing the workload by designers and making the process much more efficient. In this paper, we conduct a comprehensive review of three major research topics of architecture layout design and generation: floorplan layout generation, scene layout synthesis, and generation of some other formats of building layouts. For each topic, we present an overview of the leading paradigms, categorized either by research domains (architecture or machine learning) or by user input conditions or constraints. We then introduce the commonly-adopted benchmark datasets that are used to verify the effectiveness of the methods, as well as the corresponding evaluation metrics. Finally, we identify the well-solved problems and limitations of existing approaches, then propose new perspectives as promising directions for future research in this important research area. A project associated with this survey to maintain the resources is available at awesome-building-layout-generation.

Problem

• Reviewing computer-aided building layout generation methods
• Comparing traditional and deep learning-based layout design approaches
• Identifying challenges and future directions in layout generation

Innovation

• Deep generative models improve layout fidelity
• Comprehensive review of architecture layout paradigms
• Benchmark datasets verify method effectiveness