Boundary representation (B-rep) is the de facto standard for CAD model representation in modern industrial design. The intricate coupling between geometric and topological elements in B-rep structures has forced existing generative methods to rely on cascaded multi-stage networks, resulting in error accumulation and computational inefficiency. We present BrepGPT, a single-stage autoregressive framework for B-rep generation. Our key innovation lies in the Voronoi Half-Patch (VHP) representation, which decomposes B-reps into unified local units by assigning geometry to nearest half-edges and sampling their next pointers. Unlike hierarchical representations that require multiple distinct encodings for different structural levels, our VHP representation facilitates unifying geometric attributes and topological relations in a single, coherent format. We further leverage dual VQ-VAEs to encode both vertex topology and Voronoi Half-Patches into vertex-based tokens, achieving a more compact sequential encoding. A decoder-only Transformer is then trained to autoregressively predict these tokens, which are subsequently mapped to vertex-based features and decoded into complete B-rep models. Experiments demonstrate that BrepGPT achieves state-of-the-art performance in unconditional B-rep generation. The framework also exhibits versatility in various applications, including conditional generation from category labels, point clouds, text descriptions, and images, as well as B-rep autocompletion and interpolation.

翻译：边界表示（B-rep）是现代工业设计中CAD模型表示的事实标准。B-rep结构中几何与拓扑元素之间错综复杂的耦合关系，迫使现有生成方法依赖级联的多阶段网络，导致误差累积和计算效率低下。本文提出BrepGPT，一种用于B-rep生成的单阶段自回归框架。我们的核心创新在于Voronoi半补丁（VHP）表示，该方法通过将几何分配给最近半边并采样其下一指针，将B-rep分解为统一的局部单元。与需要为不同结构层次使用多种独立编码的分层表示不同，我们的VHP表示能够以单一连贯格式统一几何属性与拓扑关系。我们进一步利用双重VQ-VAE将顶点拓扑和Voronoi半补丁编码为基于顶点的标记，实现更紧凑的序列编码。随后训练仅解码器Transformer自回归预测这些标记，这些标记被映射至基于顶点的特征并解码为完整B-rep模型。实验表明，BrepGPT在无条件B-rep生成中达到最先进性能。该框架还展现出在多种应用中的通用性，包括基于类别标签、点云、文本描述和图像的条件生成，以及B-rep自动补全与插值。