用手绘草图自动生成3D建筑模型，人机协作提升精度
Sketch2BIM: A Multi-Agent Human-AI Collaborative Pipeline to Convert Hand-Drawn Floor Plans to 3D BIM
- 多智能体框架结合大语言模型解析草图并迭代优化
- 墙、门、窗识别精确度达F1超0.83，几何误差趋近于零
- 非专业人士也能通过手绘完成专业级建筑建模
本研究提出一种人机协同的全流程方法，将未缩放的手绘平面草图转化为语义一致的3D BIM模型。该流程在多智能体框架中利用多模态大语言模型（MLLM），整合感知提取、人工反馈、结构校验与自动化BIM脚本生成。初始阶段，草图被迭代优化为包含墙体、门窗的结构化JSON布局；随后转换为可执行脚本生成3D BIM模型。在十组多样化的平面图上实验表明：门窗在首次迭代中即可高可靠捕捉，墙体检测准确率初始约83%，经数轮反馈后接近完美对齐。所有类别中，精确率、召回率和F1值均高于0.83，几何误差（RMSE、MAE）随反馈逐步降为零。结果表明，基于MLLM的多智能体推理可使建筑信息模型创建面向专家与非专业人士开放。
原文摘要 · Abstract (English)
This study introduces a human-in-the-loop pipeline that converts unscaled, hand-drawn floor plan sketches into semantically consistent 3D BIM models. The workflow leverages multimodal large language models (MLLMs) within a multi-agent framework, combining perceptual extraction, human feedback, schema validation, and automated BIM scripting. Initially, sketches are iteratively refined into a structured JSON layout of walls, doors, and windows. Later, these layouts are transformed into executable scripts that generate 3D BIM models. Experiments on ten diverse floor plans demonstrate strong convergence: openings (doors, windows) are captured with high reliability in the initial pass, while wall detection begins around 83% and achieves near-perfect alignment after a few feedback iterations. Across all categories, precision, recall, and F1 scores remain above 0.83, and geometric errors (RMSE, MAE) progressively decrease to zero through feedback corrections. This study demonstrates how MLLM-driven multi-agent reasoning can make BIM creation accessible to both experts and non-experts using only freehand sketches.
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。