arXiv:2601.09428cs.LGcs.GR2026-01被引 1

用尺规作图步骤教模型生成可参数化编辑的CAD图形

Draw it like Euclid: Teaching transformer models to generate CAD profiles using ruler and compass construction steps

  • 通过尺规作图步骤逐步构建几何形状,类似思维链提升生成质量
  • 构造序列将自由度降至少数参数,支持高精度参数化编辑
  • 强化学习优化作图序列,提升多维度性能,含未显式优化指标

我们提出一种新方法,通过一系列简单的几何构造步骤(如偏移、旋转、交点)生成计算机辅助设计(CAD)轮廓。这些步骤从设计师提供的初始几何出发,逐步构建出最终轮廓的点和曲线。实验表明,在初始几何与最终轮廓之间加入构造步骤,能显著提升生成质量,类似于语言模型中的思维链机制。与参数化CAD模型类似,构造序列将形状自由度限制为少量可调节参数,支持基于构造结果的浮点精度参数化编辑。此外,我们通过强化学习优化构造序列,在多个评估指标上取得进一步提升,包括一些未直接优化的指标。

原文摘要 · Abstract (English)

We introduce a new method of generating Computer Aided Design (CAD) profiles via a sequence of simple geometric constructions including curve offsetting, rotations and intersections. These sequences start with geometry provided by a designer and build up the points and curves of the final profile step by step. We demonstrate that adding construction steps between the designer's input geometry and the final profile improves generation quality in a similar way to the introduction of a chain of thought in language models. Similar to the constraints in a parametric CAD model, the construction sequences reduce the degrees of freedom in the modeled shape to a small set of parameter values which can be adjusted by the designer, allowing parametric editing with the constructed geometry evaluated to floating point precision. In addition we show that applying reinforcement learning to the construction sequences gives further improvements over a wide range of metrics, including some which were not explicitly optimized.

CAD生成几何建模强化学习参数化

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。