Text2CAD: Text to 3D CAD Generation via Technical Drawings

TL;DR

Text2CAD is introduced, a novel framework that employs stable diffusion models tailored to automate the generation process and efficiently bridge the gap between user specifications in text and functional CAD models, showing substantial potential to revolutionize CAD automation in response to user demands.

Abstract

The generation of industrial Computer-Aided Design (CAD) models from user requests and specifications is crucial to enhancing efficiency in modern manufacturing. Traditional methods of CAD generation rely heavily on manual inputs and struggle with complex or non-standard designs, making them less suited for dynamic industrial needs. To overcome these challenges, we introduce Text2CAD, a novel framework that employs stable diffusion models tailored to automate the generation process and efficiently bridge the gap between user specifications in text and functional CAD models. This approach directly translates the user's textural descriptions into detailed isometric images, which are then precisely converted into orthographic views, e.g., top, front, and side, providing sufficient information to reconstruct 3D CAD models. This process not only streamlines the creation of CAD models from textual descriptions but also ensures that the resulting models uphold physical and dimensional consistency essential for practical engineering applications. Our experimental results show that Text2CAD effectively generates technical drawings that are accurately translated into high-quality 3D CAD models, showing substantial potential to revolutionize CAD automation in response to user demands.

Figures (15)

• Figure 1: Overview of our method. Our method converts textual descriptions into a 3D CAD model through a multi-step process. First, the text is transformed into an isometric image representing the described features. This image is then mapped into orthographic technical drawings, which serve as the foundation for generating the 3D CAD model.
• Figure 2: Overall view of our Text2CAD framework. The dataset creation process involves (a) generating technical drawings from a CAD model and (b) producing textual descriptions of the CAD model using GPT-4. The CAD generation process includes (c) generating isometric images based on the textual descriptions, (d) deriving orthographic technical drawings from the generated isometric images, and finally, (e) reconstructing the CAD model from the generated orthographic technical drawings.
• Figure 3: Rendered technical drawings. Isometric images and the orthographic technical drawings of the CAD models.
• Figure 4: Generated descriptions. GPT-4 receives isometric images and provides descriptions within a template.
• Figure 5: Technical drawings by a stable diffusion model. The images are generated by Stable Diffusion v1-5.