AI 中文总结
研究针对AEC图纸信息提取难题，构建特定数据集，对五种深度学习架构进行基准测试，RF-DETR和Qwen3-VL表现出色，而通用预训练模型有域干扰，为AEC自动化信息提取奠定技术基础。
AI 中文摘要
建筑、工程和施工（AEC）图纸的信息提取因人工效率低下而受阻，而布局检测作为组织图形和文本层次结构的关键“中间件”却未得到充分探索。针对以文本为中心的内容优化的通用文档布局模型，未在工程图纸上进行验证。本研究构建了一个定制的AEC特定布局数据集，并对五种深度学习架构进行基准测试。RF-DETR以0.949的mAP50实现了当前最优性能，视觉语言模型Qwen3-VL获得了0.911的领先F1分数。相反，在通用文档数据集上预训练的模型存在“域干扰”，导致性能下降。这为AEC中的自动化信息提取建立了强大的技术基础。
英文摘要
Information Extraction (IE) from Architecture, Engineering, and Construction (AEC) drawings remains hindered by manual inefficiency, while Layout Detection, a vital 'middleware' organizing graphical and textual hierarchies, is underexplored. General document layout models, optimized for text-centric content, lack validation on engineering drawings. This study constructs a custom AEC-specific layouts dataset and benchmarks five deep learning architectures. RF-DETR achieves state-of-the-art performance with an $mAP_{50}$ of 0.949, while the Vision-Language Model Qwen3-VL attains a leading F1-score of 0.911. Conversely, models pre-trained on general document datasets suffer from "domain interference", causing performance degradation. This establishes a robust technical foundation for automated IE in AEC.
Comments2026 European Conference of Computing in Construction (EC3 2026), 8 pages
