FoV-Net：基于视场射线投射的旋转不变 CAD B-rep 学习
FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting
用局部参考系 UV 网格加视线射线投射构造旋转不变的逐面表征，再经图注意力在 B-rep 图上传播，这套「局部几何 + 射线采样上下文」的思路可直接迁移到点云、网格等 3D 表示上做 SO(3) 不变的特征学习。
原文依据 captures both local surface geometry and global structural context in a rotation-invariant manner
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论直接从边界表示（B-rep）学习已显著推进了三维 CAD 分析。然而，最优的 B-rep 学习方法依赖绝对坐标与法向来编码全局上下文，因而对旋转高度敏感。我们的实验表明，在对齐基准上达到 95% 以上准确率的模型，在任意 SO(3) 旋转下准确率可骤降至 10%。为解决这一问题，我们提出 FoV-Net，这是首个以旋转不变方式同时捕捉局部曲面几何与全局结构上下文的 B-rep 学习框架。每个面由一个局部参考系（LRF）UV 网格表示，以编码其局部曲面几何；并由视场（FoV）网格表示，通过投射射线并记录与相邻面的交点来捕捉周围的三维上下文。轻量级 CNN 提取逐面特征，这些特征借助图注意力网络在 B-rep 图上传播。FoV-Net 在 B-rep 分类与分割基准上取得最优性能，展现出对任意旋转的鲁棒性，同时达到强结果所需的训练数据也更少。
英文原文摘要 1166 字符
Learning directly from boundary representations (B-reps) has significantly advanced 3D CAD analysis. However, state-of-the-art B-rep learning methods rely on absolute coordinates and normals to encode global context, making them highly sensitive to rotations. Our experiments reveal that models achieving over 95% accuracy on aligned benchmarks can collapse to as low as 10% under arbitrary SO(3) rotations. To address this, we introduce FoV-Net, the first B-rep learning framework that captures both local surface geometry and global structural context in a rotation-invariant manner. Each face is represented by a Local Reference Frame (LRF) UV-grid that encodes its local surface geometry, and by Field-of-View (FoV) grids that capture the surrounding 3D context by casting rays and recording intersections with neighboring faces. Lightweight CNNs extract per-face features, which are propagated over the B-rep graph using a graph attention network. FoV-Net achieves state-of-the-art performance on B-rep classification and segmentation benchmarks, demonstrating robustness to arbitrary rotations while also requiring less training data to achieve strong results.