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

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 d...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-09
Main Authors: Khan, Mohammad Sadil, Sinha, Sankalp, Talha Uddin Sheikh, Stricker, Didier, Sk Aziz Ali, Afzal, Muhammad Zeshan
Format: Article
Language:English
Subjects:
Annotations
CAD
Computer aided design
Concentric cylinders
Datasets
Design
Natural language processing
Prototyping
Source code
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422