NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling
This addresses the challenge of text-to-CAD generation for designers and engineers, offering a novel approach that improves over prior methods but is incremental in its hybrid representation.
The paper tackles the problem of generating editable 3D CAD models from natural language by introducing NURBGen, a framework that uses a fine-tuned LLM to translate text into NURBS parameters, achieving high geometric fidelity and dimensional accuracy as confirmed by expert evaluations.
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.