CAD编辑器：一种具有自动训练数据综合的“先定位后填充”框架，用于基于文本的CAD编辑。

CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing

February 6, 2025

作者: Yu Yuan, Shizhao Sun, Qi Liu, Jiang Bian

cs.AI

摘要

计算机辅助设计（CAD）在各行各业中都是不可或缺的。 基于文本的CAD编辑自动化修改CAD模型的过程，具有巨大潜力但仍未得到充分探索。 现有方法主要集中在设计变体生成或基于文本的CAD生成，要么缺乏对基于文本的控制的支持，要么忽视现有CAD模型作为约束条件。 我们介绍了CAD-Editor，这是第一个基于文本的CAD编辑框架。 为了解决训练过程中需要准确对应的三元数据的挑战，我们提出了一个自动化数据合成流水线。 该流水线利用设计变体模型生成原始CAD模型和编辑后CAD模型的配对，并利用大型视觉语言模型（LVLMs）将它们的差异总结为编辑指令。 为了解决基于文本的CAD编辑的复合性质，我们提出了一个定位-填充框架，将任务分解为两个专注的子任务：定位需要修改的区域，然后填充这些区域以进行适当的编辑。 大型语言模型（LLMs）作为这两个子任务的支柱，利用其在自然语言理解和CAD知识方面的能力。 实验证明，CAD-Editor在定量和定性方面均取得了优越的性能。

English

Computer Aided Design (CAD) is indispensable across various industries. Text-based CAD editing, which automates the modification of CAD models based on textual instructions, holds great potential but remains underexplored. Existing methods primarily focus on design variation generation or text-based CAD generation, either lacking support for text-based control or neglecting existing CAD models as constraints. We introduce CAD-Editor, the first framework for text-based CAD editing. To address the challenge of demanding triplet data with accurate correspondence for training, we propose an automated data synthesis pipeline. This pipeline utilizes design variation models to generate pairs of original and edited CAD models and employs Large Vision-Language Models (LVLMs) to summarize their differences into editing instructions. To tackle the composite nature of text-based CAD editing, we propose a locate-then-infill framework that decomposes the task into two focused sub-tasks: locating regions requiring modification and infilling these regions with appropriate edits. Large Language Models (LLMs) serve as the backbone for both sub-tasks, leveraging their capabilities in natural language understanding and CAD knowledge. Experiments show that CAD-Editor achieves superior performance both quantitatively and qualitatively.