Engineering Drawing
Engineering drawing analysis is undergoing a rapid transformation driven by advancements in computer vision and deep learning. Current research focuses on automating tasks like symbol recognition, component segmentation, and text extraction from drawings, often employing graph neural networks (GNNs), convolutional neural networks (CNNs), and generative adversarial networks (GANs) to process both raster and vector data. These methods aim to improve efficiency in various industries, such as manufacturing and construction, by enabling automated tasks like CAD conversion, BIM creation, and quality control. The ultimate goal is to move beyond manual interpretation of engineering drawings, leading to faster, more accurate, and less labor-intensive workflows.
Papers
From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach
Xilin Wang, Jia Zheng, Yuanchao Hu, Hao Zhu, Qian Yu, Zihan Zhou
LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model
Xi Wang, Hongzhen Li, Heng Fang, Yichen Peng, Haoran Xie, Xi Yang, Chuntao Li