From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach

TL;DR

This paper introduces CAD2Program, a vision-language model that reconstructs 3D parametric models from 2D CAD drawings by encoding images with ViT and generating descriptive text, offering flexibility and competitive performance.

Contribution

The paper presents a novel vision-language approach for 3D model reconstruction from 2D CAD drawings, using image encoding and text generation, departing from traditional vector-based methods.

Findings

Achieves competitive performance with fewer restrictions on input drawings.

Uses a flexible text-based representation for 3D models.

Demonstrates effectiveness on a large-scale cabinet dataset.

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.