基于 B-rep 整体词元序列表示的自回归生成
AutoRegressive Generation with B-rep Holistic Token Sequence Representation
把 B-rep 的几何与拓扑统一编码成单一词元序列，使 Transformer 自回归生成框架可直接用于 CAD 边界表示生成；对做 3D 生成与结构化几何表示的人，这是一条把图结构转成序列、从而复用语言模型式生成范式的可复用思路。
原文依据 encode B-rep's geometry and topology into a holistic token sequence representation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论以往针对 B-rep 的表示与生成方法依赖基于图的表示，通过解耦的计算流程将几何特征与拓扑特征分离，从而无法应用基于序列的生成框架，例如已展现出卓越性能的 Transformer 架构。本文提出 BrepARG，首次尝试将 B-rep 的几何与拓扑编码为整体词元序列表示，从而以自回归架构实现基于序列的 B-rep 生成。具体而言，BrepARG 将 B-rep 编码为三类词元：表示几何特征的几何词元与位置词元，以及表示拓扑的面索引词元。随后以层次化方式构建整体词元序列：先利用上述词元构建几何块（即面与边），再进行几何块排序，最终组装出整个 B-rep 的整体序列表示。我们还构建了一个基于 Transformer 的自回归模型，采用带因果掩码的多层仅解码器架构，通过下一词元预测学习整体词元序列上的分布。实验表明 BrepARG 取得了最优性能。BrepARG 验证了将 B-rep 表示为整体词元序列的可行性，为 B-rep 生成开辟了新的方向。
英文原文摘要 1441 字符
Previous representation and generation approaches for the B-rep relied on graph-based representations that disentangle geometric and topological features through decoupled computational pipelines, thereby precluding the application of sequence-based generative frameworks, such as transformer architectures that have demonstrated remarkable performance. In this paper, we propose BrepARG, the first attempt to encode B-rep's geometry and topology into a holistic token sequence representation, enabling sequence-based B-rep generation with an autoregressive architecture. Specifically, BrepARG encodes B-rep into 3 types of tokens: geometry and position tokens representing geometric features, and face index tokens representing topology. Then the holistic token sequence is constructed hierarchically, starting with constructing the geometry blocks (i.e., faces and edges) using the above tokens, followed by geometry block sequencing. Finally, we assemble the holistic sequence representation for the entire B-rep. We also construct a transformer-based autoregressive model that learns the distribution over holistic token sequences via next-token prediction, using a multi-layer decoder-only architecture with causal masking. Experiments demonstrate that BrepARG achieves state-of-the-art (SOTA) performance. BrepARG validates the feasibility of representing B-rep as holistic token sequences, opening new directions for B-rep generation.