将电路图向量转为图结构，提升AI对工程图纸的逻辑理解能力
Beyond Pixels: Vector-to-Graph Transformation for Reliable Schematic Auditing
- 将CAD图纸的矢量信息转化为节点和边组成的属性图，显式表达元件连接关系
- 在电气合规性检测任务中，新方法准确率显著提升，而主流多模态模型接近随机猜测
- 适合需要精确结构推理的工程AI应用，如芯片设计、自动审查系统
多模态大语言模型在视觉理解方面取得显著进展，但存在关键缺陷：结构盲视。即使最先进的模型也无法捕捉工程原理图中的拓扑关系与符号逻辑，因其基于像素的范式会丢失依赖矢量定义的显式关系。为此，我们提出矢量到图（V2G）转换流程，将CAD图转化为属性图，其中节点代表元件，边编码连接关系，使结构依赖关系显式且可机器审计。在电气合规性检查诊断基准上，V2G在所有错误类别中均实现显著准确率提升，而领先的多模态模型仍处于随机水平。结果表明，基于像素的方法存在系统性不足，而结构感知表示为多模态AI在工程领域的实用部署提供了可靠路径。为促进后续研究，我们公开了基准数据集与实现代码，地址为 https://github.com/gm-embodied/V2G-Audit。
原文摘要 · Abstract (English)
Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structural blindness. Even state-of-the-art models fail to capture topology and symbolic logic in engineering schematics, as their pixel-driven paradigm discards the explicit vector-defined relations needed for reasoning. To overcome this, we propose a Vector-to-Graph (V2G) pipeline that converts CAD diagrams into property graphs where nodes represent components and edges encode connectivity, making structural dependencies explicit and machine-auditable. On a diagnostic benchmark of electrical compliance checks, V2G yields large accuracy gains across all error categories, while leading MLLMs remain near chance level. These results highlight the systemic inadequacy of pixel-based methods and demonstrate that structure-aware representations provide a reliable path toward practical deployment of multimodal AI in engineering domains. To facilitate further research, we release our benchmark and implementation at https://github.com/gm-embodied/V2G-Audit.
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。