ChatCAD: An MLLM-Guided Framework for Zero-shot CAD Drawing Restoration

• Published in: Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 1 - 5
• Main Authors: Tang, Jing, Xiao, Hongru, Li, Xiang, Wang, Wei, Gong, Zeyu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 06.04.2025
• Subjects: Adaptation models; Digital CAD drawing Restoration; Large Language Model; Large language models; Maintenance engineering; Multi-agent systems; Multimodal Large Language Model; Robustness; Signal processing; Software; Software reliability; Solid modeling; Speech processing
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP49660.2025.10890248

CAD drawing restoration is one of the most urgent needs in industrial manufacturing. The existing research focuses on the digitization of CAD drawings, However, there are actually many problems in digitized CAD drawings due to the upgrading of engineering drafting software, and it is difficult to repair reliably. In this paper, we use multi-modal large language models (MLLMs) to carry out digital CAD drawing restoration, and we use Retrieval-Augmented Generation (RAG) technology to inject engineering domain knowledge into MLLMs. In addition, a complete set of multiagent systems is constructed to realize restoration in accordance with the CAD drawing review process in the mechanical field. We collected 1,639 CAD drawings of bearing seats to evaluate our multi-agent system, verifying its reliability and robustness to various problematic drawings. Notably, ChatCAD also has a much simpler implementation than alternative methods trained on a huge dataset.