发表机构
The University of Hong Kong; Deemos Technology Co., Ltd.; Institute of Software, Chinese Academy of Sciences; ShanghaiTech University; Texas A&M University（香港大学; 迪莫斯科技有限公司; 中国科学院软件研究所; 上海科技大学; 德克萨斯A&M大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出 ParaCAD 自回归框架，用于点云条件 B-Rep 生成，直接在原生参数曲面上运行，通过以曲面为中心的令牌化编码面信息，先生成参数曲面再构建 B-Rep，实验证明其在多方面优于基于点的基线。
AI 中文摘要
生成式 CAD 建模具有广泛的设计和应用潜力。尽管在 CAD 中的主导表示形式边界表示（B-Rep）生成方面取得了重大进展，但现有方法很大程度上依赖基于均匀采样点或网格的几何表示，牺牲了原生曲面类型和参数，限制了几何保真度和下游可用性。我们提出了 ParaCAD，一种用于点云条件 B-Rep 生成的自回归框架，它直接在原生参数曲面上运行。ParaCAD 引入了以曲面为中心的令牌化，通过其确切曲面类型和连续参数对每个面进行显式编码。模型先生成具有受限 UV 域的参数曲面，然后通过全局相交这些曲面来构建有效的 B-Rep 以恢复边和顶点。大量实验表明，ParaCAD 能生成具有忠实点云对齐的准确 B-Rep，在几何精度、鲁棒性、水密性和下游可用性方面优于基于点的基线。
英文摘要
Generative CAD modeling has broad design and application potential. Despite significant advances in Boundary Representation (B-Rep) generation, the dominant representation in CAD, existing methods largely depend on uniformly sampled point- or grid-based geometry representations, sacrificing native surface types and parameters and thereby limiting geometric fidelity and downstream usability. We present ParaCAD, an autoregressive framework for point-cloud-conditioned B-Rep generation that directly operates on native parametric surfaces. ParaCAD introduces a surface-centric tokenization that explicitly encodes each face by its exact surface type and continuous parameters, preserving the intrinsic semantics of CAD geometry. Our model first generates parametric surfaces with constrained UV domains, and then constructs a valid B-Rep by globally intersecting these surfaces to recover edges and vertices. ParaCAD places point-cloud-conditioned generation at the core of B-Rep synthesis, making it practical for user-guided reconstruction and seamless integration into existing 3D generation pipelines. Extensive experiments demonstrate that ParaCAD produces accurate B-Reps with faithful point-cloud alignment, outperforming point-based baselines in geometric precision, robustness, watertightness and downstream usability.
