ChatHouseDiffusion: Prompt-Guided Generation and Editing of Floor Plans
This addresses the need for more flexible and efficient floor plan design tools for architects, though it appears incremental as it builds on existing diffusion and LLM methods.
The paper tackles the problem of generating and editing floor plans in architectural planning by introducing ChatHouseDiffusion, which uses LLMs, graphormer, and diffusion models to interpret natural language and enable iterative adjustments. The result is higher IoU scores compared to existing models, allowing precise, localized edits without complete redesigns.
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.