AI & text-to-CAD
Neural CAD
Definition
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.
Also known as: neural CAD models, CAD foundation models
Updated
Research and product use#
In research, the idea goes back at least to DeepCAD, which generated CAD models as sequences of construction operations rather than meshes or point clouds. Later work such as Text2CAD conditioned those sequences on text.
As a product name, Autodesk's 2026 Fusion roadmap says it is working toward neural CAD experiences that turn natural language prompts into editable design geometry. Check the current release notes before assuming any specific capability has shipped.
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.
Text2CAD
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.
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.
Feature tree
A feature tree is the ordered list of operations, such as sketches, extrudes, cuts, fillets, and patterns, that builds a parametric CAD model. Editing an early feature replays every feature after it, which makes controlled changes possible and also makes the model depend on each earlier step.