用大模型先构思布局，再用扩散模型精修，生成更精准的户型图。
HouseTune: Two-Stage Floorplan Generation with LLM Assistance
- 分两阶段：先用大模型理解语言描述生成初稿
- 再用扩散模型优化几何结构，符合实际建房约束
- 无需大量专业数据训练，适合普通用户快速设计
本文提出一种两阶段文本到户型图生成框架，结合大语言模型（LLM）的推理能力与扩散模型的生成优势。第一阶段采用思维链（CoT）提示策略，引导LLM从自然语言描述生成初始布局（Layout-Init），提升设计过程的用户友好性。但Layout-Init可能缺乏精确的几何对齐和细粒度结构细节。第二阶段引入条件扩散模型，将Layout-Init精细化为最终户型图（Layout-Final），更好地满足物理约束与用户需求。相比以往方法，该框架在无需大量领域特定训练数据的情况下，显著降低了学习难度。实验表明，该方法在所有指标上均达到当前最优性能，验证了其在实际家居设计中的有效性。
原文摘要 · Abstract (English)
This paper proposes a two-stage text-to-floorplan generation framework that combines the reasoning capability of Large Language Models (LLMs) with the generative power of diffusion models. In the first stage, we leverage a Chain-of-Thought (CoT) prompting strategy to guide an LLM in generating an initial layout (Layout-Init) from natural language descriptions, which ensures a user-friendly and intuitive design process. However, Layout-Init may lack precise geometric alignment and fine-grained structural details. To address this, the second stage employs a conditional diffusion model to refine Layout-Init into a final floorplan (Layout-Final) that better adheres to physical constraints and user requirements. Unlike prior methods, our approach effectively reduces the difficulty of floorplan generation learning without the need for extensive domain-specific training data. Experimental results demonstrate that our approach achieves state-of-the-art performance across all metrics, which validates its effectiveness in practical home design applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。