Pointer-CAD：通过基于指针的边与面选择统一 B-Rep 与命令序列
Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection
将 B-rep 的几何实体选择建模为指针网络预测，为视觉-语言模型在结构化几何生成中提供可复用的实体引用机制；同时其数据标注流水线可启发 3D 理解任务中的自然语言监督构建。
原文依据 the LLM predicts a Pointer that selects the most feature-consistent candidate from the available set
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论构建计算机辅助设计（CAD）模型是劳动密集型工作，但对工程和制造至关重要。大语言模型（LLM）的最新进展启发了基于 LLM 的 CAD 生成，其将 CAD 表示为命令序列。但这些方法在实际场景中面临困难，因为命令序列表示不支持实体选择（例如面或边），限制了其支持倒角或圆角等复杂编辑操作的能力。此外，在草图与拉伸操作中对连续变量的离散化可能导致拓扑错误。为解决这些限制，我们提出了 Pointer-CAD，一种新颖的基于 LLM 的 CAD 生成框架，它利用基于指针的命令序列表示，将 B-rep 模型的几何信息显式地融入序列建模。具体而言，Pointer-CAD 将 CAD 模型生成分解为多个步骤，每个后续步骤的生成均以文本描述和前序步骤生成的 B-rep 为条件。当某个操作需要选择特定几何实体时，LLM 预测一个指针，从可用集合中选择特征最一致的候选。这种选择操作还减少了基于命令序列表示中的量化误差。为支持 Pointer-CAD 的训练，我们开发了一个数据标注流水线，用于生成专家级自然语言描述，并应用它构建了约 575K 个 CAD 模型的数据集。大量实验结果表明，Pointer-CAD 有效支持复杂几何结构的生成，并将分割误差降至极低水平，相较于先前的命令序列方法取得了显著改进，从而大幅缓解了量化误差引入的拓扑不准确性问题。我们的代码可在 https://github.com/Snitro/Pointer-CAD 获取。
英文原文摘要 1967 字符
Constructing computer-aided design (CAD) models is labor-intensive but essential for engineering and manufacturing. Recent advances in Large Language Models (LLMs) have inspired the LLM-based CAD generation by representing CAD as command sequences. But these methods struggle in practical scenarios because command sequence representation does not support entity selection (e.g. faces or edges), limiting its ability to support complex editing operations such as chamfer or fillet. Further, the discretization of a continuous variable during sketch and extrude operations may result in topological errors. To address these limitations, we present Pointer-CAD, a novel LLM-based CAD generation framework that leverages a pointer-based command sequence representation to explicitly incorporate the geometric information of B-rep models into sequential modeling. In particular, Pointer-CAD decomposes CAD model generation into steps, conditioning the generation of each subsequent step on both the textual description and the B-rep generated from previous steps. Whenever an operation requires the selection of a specific geometric entity, the LLM predicts a Pointer that selects the most feature-consistent candidate from the available set. Such a selection operation also reduces the quantization error in the command sequence-based representation. To support the training of Pointer-CAD, we develop a data annotation pipeline that produces expert-level natural language descriptions and apply it to build a dataset of approximately 575K CAD models. Extensive experimental results demonstrate that Pointer-CAD effectively supports the generation of complex geometric structures and reduces segmentation error to an extremely low level, achieving a significant improvement over prior command sequence methods, thereby significantly mitigating the topological inaccuracies introduced by quantization error. Our code is available at https://github.com/Snitro/Pointer-CAD.