AI-Driven Design and Generative Architecture

ChatHouseDiffusion: Prompt-Guided Generation and Editing of Floor Plans

Sizhong Qin, Chengyu He, Qiaoyun Chen, Sen Yang, Wenjie Liao, Yi Gu, Xinzheng Lu

Published 2024-10-15

Thumbnail for ChatHouseDiffusion: Prompt-Guided Generation and Editing of Floor Plans
📄 Paper
The generation and editing of floor plans are critical in architectural planning, requiring a high degree of flexibility and efficiency. Existing methods demand extensive input information and lack the capability for interactive adaptation to user modifications. This paper introduces ChatHouseDiffusion, which leverages large language models (LLMs) to interpret natural language input, employs graphormer to encode topological relationships, and uses diffusion models to flexibly generate and edit floor plans. This approach allows iterative design adjustments based on user ideas, significantly enhancing design efficiency. Compared to existing models, ChatHouseDiffusion achieves higher Intersection over Union (IoU) scores, permitting precise, localized adjustments without the need for complete redesigns, thus offering greater practicality. Experiments demonstrate that our model not only strictly adheres to user specifications but also facilitates a more intuitive design process through its interactive capabilities.

Abstract

The generation and editing of floor plans are critical in architectural planning, requiring a high degree of flexibility and efficiency. Existing methods demand extensive input information and lack the capability for interactive adaptation to user modifications. This paper introduces ChatHouseDiffusion, which leverages large language models (LLMs) to interpret natural language input, employs graphormer to encode topological relationships, and uses diffusion models to flexibly generate and edit floor plans. This approach allows iterative design adjustments based on user ideas, significantly enhancing design efficiency. Compared to existing models, ChatHouseDiffusion achieves higher Intersection over Union (IoU) scores, permitting precise, localized adjustments without the need for complete redesigns, thus offering greater practicality. Experiments demonstrate that our model not only strictly adheres to user specifications but also facilitates a more intuitive design process through its interactive capabilities.

Topics

2D floor planAR/VR/XR visualizationAR/VR interfacesGenerative Design and Design Space ExplorationInteractive VisualizationLLMs for AECdesign automationdiffusion modelsgeometry generationimmersive design

Cite this paper

@misc{qin2024chathousediffusion,
      title={ChatHouseDiffusion: Prompt-Guided Generation and Editing of Floor Plans},
      author={Sizhong Qin and Chengyu He and Qiaoyun Chen and Sen Yang and Wenjie Liao and Yi Gu and Xinzheng Lu},
      year={2024},
      eprint={2410.11908},
      archivePrefix={arXiv},
      primaryClass={cs.HC},
      url={https://arxiv.org/abs/2410.11908},
}

%%%%%% Parametric, Computational and Algorithmic Design %%%%%%