NURBGen：基于大语言模型驱动的NURBS建模实现高保真文本到CAD生成

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

November 9, 2025

作者: Muhammad Usama, Mohammad Sadil Khan, Didier Stricker, Muhammad Zeshan Afzal

cs.AI

摘要

从自然语言生成可编辑的3D CAD模型仍具挑战性，现有文本转CAD系统或生成网格模型，或依赖稀缺的设计历史数据。我们提出NURBGen——首个通过非均匀有理B样条（NURBS）直接从文本生成高保真3D CAD模型的框架。通过微调大语言模型，该系统可将自由格式文本转换为包含NURBS曲面参数（控制点、节点向量、阶数和有理权重）的JSON表示，并借助Python直接转换为BRep格式。我们进一步提出混合表示法，将未修剪NURBS与解析图元结合，以更稳健地处理修剪曲面和退化区域，同时降低标记复杂度。此外还推出partABC数据集，该精选子集源自ABC数据集，包含独立CAD组件，并通过自动化标注流程添加详细描述。专家评估证实，NURBGen在多样化提示词上表现优异，在几何保真度与尺寸精度方面超越现有方法。代码与数据集将公开发布。

English

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 (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.