PrimitiveCAD：基于LLM的点到CAD重建，采用基元感知标记化与操作对齐

中文摘要 AI 辅助

基于大模型的点云到CAD生成在推进工业设计和提升三维建模效率方面具有巨大潜力。然而，现有大多数方法将问题视为通用的点云编码和标记预测任务，忽略了专门针对CAD相关基元的标记化和监督。因此，这些方法往往难以准确重建复杂的基元结构。为解决这一局限，我们提出PrimitiveCAD，一种新颖的多阶段点云到CAD重建范式，旨在增强生成CAD模型的几何精度，同时更好地保留关键几何特征。首先，我们引入基元感知的点云标记化模型，使系统能够从CAD点云中学习更鲁棒的几何表示。其次，我们在大型语言模型（LLM）上进行监督微调，并引入操作对齐损失以对齐关键CAD操作频率，从而改善全局形状特征的保留。最后，我们整合强化学习（RL）并引入特征线对齐奖励，以进一步减少随机性并增强几何特征的细粒度保留。在DeepCAD和Fusion360数据集上的实验表明，我们的方法在代码有效性、几何精度和几何特征保留方面达到了最先进的性能。

英文摘要

Large-model-based point-to-CAD generation holds immense potential for advancing industrial design and enhancing 3D modeling efficiency. However, most existing methods approach the problem as a general point-cloud encoding and token prediction task, neglecting the tokenization and supervision specifically for CAD-related primitives. As a result, these methods often struggle to accurately reconstruct the intricate primitive structures. To address this limitation, we propose PrimitiveCAD, a novel multi-stage paradigm for point-to-CAD reconstruction that enhances the geometric accuracy of generated CAD models while better preserving critical geometric features. First, we introduce a primitive-aware point cloud tokenization model, enabling the system to learn more robust geometric representations from CAD point clouds. Next, we perform supervised finetuning on a large language model (LLM) and introduce an operation alignment loss to align key CAD operation frequencies, thereby improving the preservation of global shape features. Finally, we incorporate reinforcement learning (RL) and introduce a feature-line alignment reward to further reduce stochasticity and enhance the fine-grained preservation of geometric features. Experiments on the DeepCAD and Fusion360 datasets show that our method achieves state-of-the-art performance in code validity, geometric accuracy, and geometric feature preservation.

发表机构

• Hangzhou Dianzi University（杭州电子科技大学）

机构由 AI 辅助整理，请以论文原文为准。