Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Xilin, Zheng, Jia, Hu, Yuanchao, Zhu, Hao, Yu, Qian, Zhou, Zihan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.11892
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910748944367616
author Wang, Xilin
Zheng, Jia
Hu, Yuanchao
Zhu, Hao
Yu, Qian
Zhou, Zihan
author_facet Wang, Xilin
Zheng, Jia
Hu, Yuanchao
Zhu, Hao
Yu, Qian
Zhou, Zihan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11892
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach
Wang, Xilin
Zheng, Jia
Hu, Yuanchao
Zhu, Hao
Yu, Qian
Zhou, Zihan
Computer Vision and Pattern Recognition
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.
title From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.11892