Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts

TL;DR

Text2CAD is an AI framework that converts natural language instructions into parametric CAD models, enabling users of all skill levels to rapidly generate complex designs with high accuracy.

Contribution

The paper introduces the first end-to-end transformer-based system for text-to-parametric CAD generation and a large annotated dataset for training and evaluation.

Findings

High-quality CAD models generated from text prompts

Effective performance across various complexity levels

Potential to accelerate and democratize CAD design processes

Abstract

Prototyping complex computer-aided design (CAD) models in modern softwares can be very time-consuming. This is due to the lack of intelligent systems that can quickly generate simpler intermediate parts. We propose Text2CAD, the first AI framework for generating text-to-parametric CAD models using designer-friendly instructions for all skill levels. Furthermore, we introduce a data annotation pipeline for generating text prompts based on natural language instructions for the DeepCAD dataset using Mistral and LLaVA-NeXT. The dataset contains $\sim170$K models and $\sim660$K text annotations, from abstract CAD descriptions (e.g., generate two concentric cylinders) to detailed specifications (e.g., draw two circles with center $(x,y)$ and radius $r_{1}$, $r_{2}$, and extrude along the normal by $d$...). Within the Text2CAD framework, we propose an end-to-end transformer-based auto-regressive network to generate parametric CAD models from input texts. We evaluate the performance of our model through a mixture of metrics, including visual quality, parametric precision, and geometrical accuracy. Our proposed framework shows great potential in AI-aided design applications. Our source code and annotations will be publicly available.