LMM4-IC4K: A Large Multimodal Model Powered Integrated Circuit Footprint Geometry Understanding

Printed-Circuit-board (PCB) footprint geometry labeling of integrated circuits (IC) is essential in defining the physical interface between components and the PCB layout, requiring precise visual perception. However, the unstructured nature of footprint drawings and abstract diagram annotations prevents direct IC footprint parsing and automated package geometry labeling methods from developing. Existing Large Multimodal Models (LMMs) struggle with inaccurate geometric perception, limiting their effectiveness in this task. To address these challenges, we propose LMM4-IC4K, a novel framework that treats IC mechanical drawings as images and leverages LMMs for structured geometric interpretation. To support such a framework, we introduce ICGeo8K, a multi-modal dataset with 8,608 labeled samples, including 4138 real-world IC footprint samples and 4470 synthetically generated samples. We further present a two-stage training framework to fine-tune LMMs for IC footprint labeling. Extensive experiments demonstrate that our model outperforms state-of-the-art LMMs on the proposed benchmark. The accurate translation of footprint diagrams enabled by LMM4-IC4K contributes to advancing automation and standardization within the PCB industry.

Designing printed circuit boards (PCBs) requires engineers to manually interpret complex technical diagrams to create precise physical layouts for integrated circuits (IC) chips. This slow, error-prone process can lead to faulty electrical connections, yet existing general-purpose Large Multimodal Models (LMMs) struggle to understand these dense, unstructured drawings. To solve this, we developed LMM4-IC4K, a specialized LMM framework designed to read IC footprint diagrams as images and automatically extract their exact geometric details. We trained this model using ICGeo8K, a newly created dataset of over 8,600 real and synthesized footprint diagrams. Experiments show LMM4-IC4K dramatically outperforms general-purpose LMMs and manual industry baselines in IC footprint interpreting accuracy. Furthermore, it completes the task 28 times faster and is over 400 times more cost-effective than traditional manual methods. Ultimately, this research paves the way for fully automated, reliable, and standardized electronics manufacturing.