Split-and-Fit：通过结构感知的 Voronoi 分区学习 B-Rep
Split-and-Fit: Learning B-Reps via Structure-Aware Voronoi Partitioning
AI总结：
本文提出 Split-and-Fit 框架，利用 NVD-Net 从点云或距离场预测基元 Voronoi 分区并逐区拟合，显著提升三维 CAD 模型 B-Rep 重建质量与泛化能力。
摘要：
我们提出了一种获取三维 CAD 模型边界表示（B-Rep）的新方法，该方法包含两步过程：首先执行称为“分割”的空间分区，随后进行“拟合”操作，以在每个分区内得到单一基元。具体而言，我们的分区旨在生成真实（GT）B-Rep 基元集合的经典 Voronoi 图。与以往通过直接基元拟合或点聚类进行自底向上构建 B-Rep 的方法不同，我们的 Split-and-Fit 方法是自顶向下且具备结构感知能力的，因为 Voronoi 分区能够显式揭示基元的数量及其相互连接关系。我们设计了一个神经网络，通过二分类从输入点云或距离场预测 Voronoi 图。我们表明，这个被命名为 NVD-Net（用于神经 Voronoi 图）的网络能够从训练数据中有效学习 CAD 模型的 Voronoi 分区，并展现出优越的泛化能力。大量实验和评估证明，所得由参数化曲面、曲线和顶点组成的 B-Rep 比现有替代方法获得的结果更加合理，重建质量取得显著提升。代码将发布于 https://github.com/yilinliu77/NVDNet。
英文摘要：
We introduce a novel method for acquiring boundary representations (B-Reps) of 3D CAD models which involves a two-step process: it first applies a spatial partitioning, referred to as the ``split``, followed by a ``fit`` operation to derive a single primitive within each partition. Specifically, our partitioning aims to produce the classical Voronoi diagram of the set of ground-truth (GT) B-Rep primitives. In contrast to prior B-Rep constructions which were bottom-up, either via direct primitive fitting or point clustering, our Split-and-Fit approach is top-down and structure-aware, since a Voronoi partition explicitly reveals both the number of and the connections between the primitives. We design a neural network to predict the Voronoi diagram from an input point cloud or distance field via a binary classification. We show that our network, coined NVD-Net for neural Voronoi diagrams, can effectively learn Voronoi partitions for CAD models from training data and exhibits superior generalization capabilities. Extensive experiments and evaluation demonstrate that the resulting B-Reps, consisting of parametric surfaces, curves, and vertices, are more plausible than those obtained by existing alternatives, with significant improvements in reconstruction quality. Code will be released on https://github.com/yilinliu77/NVDNet.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
