NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling

TL;DR

NURBGen is a novel framework that translates natural language descriptions into high-fidelity 3D CAD models using LLMs to generate NURBS representations, enabling more accurate and editable CAD model creation from text.

Contribution

This work introduces NURBGen, the first system to generate NURBS-based CAD models directly from text, combining LLM translation, hybrid NURBS representations, and a curated CAD component dataset.

Findings

Outperforms prior methods in geometric fidelity and accuracy

Successfully generates diverse CAD models from natural language prompts

Demonstrates robustness in handling complex surfaces and primitives

Abstract

Generating editable 3D CAD models from natural language remains challenging, as existing text-to-CAD systems either produce meshes or rely on scarce design-history data. We present NURBGen, the first framework to generate high-fidelity 3D CAD models directly from text using Non-Uniform Rational B-Splines (NURBS). To achieve this, we fine-tune a large language model (LLM) to translate free-form texts into JSON representations containing NURBS surface parameters (\textit{i.e}, control points, knot vectors, degrees, and rational weights) which can be directly converted into BRep format using Python. We further propose a hybrid representation that combines untrimmed NURBS with analytic primitives to handle trimmed surfaces and degenerate regions more robustly, while reducing token complexity. Additionally, we introduce partABC, a curated subset of the ABC dataset consisting of individual CAD components, annotated with detailed captions using an automated annotation pipeline. NURBGen demonstrates strong performance on diverse prompts, surpassing prior methods in geometric fidelity and dimensional accuracy, as confirmed by expert evaluations. Code and dataset will be released publicly.