From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach
Xilin Wang, Jia Zheng, Yuanchao Hu, Hao Zhu, Qian Yu, Zihan Zhou
Abstract
In this paper, we present CAD2Program, a new method for reconstructing 3D parametric models from 2D CAD drawings. Our proposed method is inspired by recent successes in vision-language models (VLMs), and departs from traditional methods which rely on task-specific data representations and/or algorithms. Specifically, on the input side, we simply treat the 2D CAD drawing as a raster image, regardless of its original format, and encode the image with a standard ViT model. We show that such an encoding scheme achieves competitive performance against existing methods that operate on vector-graphics inputs, while imposing substantially fewer restrictions on the 2D drawings. On the output side, our method auto-regressively predicts a general-purpose language describing 3D parametric models in text form. Compared to other sequence modeling methods for CAD which use domain-specific sequence representations with fixed-size slots, our text-based representation is more flexible, and can be easily extended to arbitrary geometric entities and semantic or functional properties. Experimental results on a large-scale dataset of cabinet models demonstrate the effectiveness of our method.
BibTeX
@article{Wang_Zheng_Hu_Zhu_Yu_Zhou_2025, title={From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32858}, DOI={10.1609/aaai.v39i8.32858}, abstractNote={In this paper, we present CAD2Program, a new method for reconstructing 3D parametric models from 2D CAD drawings. Our proposed method is inspired by recent successes in vision-language models (VLMs), and departs from traditional methods which rely on task-specific data representations and/or algorithms. Specifically, on the input side, we simply treat the 2D CAD drawing as a raster image, regardless of its original format, and encode the image with a standard ViT model. We show that such an encoding scheme achieves competitive performance against existing methods that operate on vector-graphics inputs, while imposing substantially fewer restrictions on the 2D drawings. On the output side, our method auto-regressively predicts a general-purpose language describing 3D parametric models in text form. Compared to other sequence modeling methods for CAD which use domain-specific sequence representations with fixed-size slots, our text-based representation is more flexible, and can be easily extended to arbitrary geometric entities and semantic or functional properties. Experimental results on a large-scale dataset of cabinet models demonstrate the effectiveness of our method.}, number={8}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wang, Xilin and Zheng, Jia and Hu, Yuanchao and Zhu, Hao and Yu, Qian and Zhou, Zihan}, year={2025}, month={Apr.}, pages={7961-7969} }