AI & text-to-CAD
Text2CAD
Definition
Text2CAD is a NeurIPS 2024 spotlight paper and dataset that generates parametric sketch-and-extrude CAD sequences from text prompts. It added about 660,000 text annotations, from beginner to expert level, to about 170,000 DeepCAD models.
Also known as: Text2CAD paper
Updated
What the paper contributed#
According to the arXiv abstract, the authors built an annotation pipeline using Mistral and LLaVA-NeXT to write text prompts for DeepCAD models, producing a dataset of about 170,000 models and 660,000 annotations. They trained a transformer to generate CAD construction sequences from those prompts. The paper was accepted to NeurIPS 2024 as a spotlight.
Because it inherits DeepCAD's operation set, Text2CAD generates sketch-and-extrude parts. It is a research baseline for text-conditioned parametric generation, not a production design tool.
Sources
Related terms
DeepCAD dataset
The DeepCAD dataset is a public research dataset of 178,238 CAD models stored as sketch-and-extrude construction sequences, released with the ICCV 2021 DeepCAD paper. Much text-to-CAD research trains and benchmarks on it, and its simple geometry limits what those models learn.
Text-to-CAD
Text-to-CAD is AI that turns a natural-language description into editable CAD geometry, such as a STEP file, a parametric model, or CAD code. The goal is a model with exact faces and dimensions that can be modified and manufactured, not just a shape that looks right on screen.
Neural CAD
Neural CAD refers to approaches where neural networks generate CAD modeling operations or editable CAD geometry, rather than meshes or images. Autodesk also uses the name for its work toward turning natural-language prompts into editable design geometry in Fusion.