# FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting

arXiv: https://arxiv.org/abs/2602.24084 · HTML: https://mlsanity.com/paper/2602.24084/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 65 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 30 of 32)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks](https://mlsanity.com/paper/2006.10503/) (2020)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [General E(2)-Equivariant Steerable CNNs](https://mlsanity.com/paper/1911.08251/) (2019)
- [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018)
- [Vector Neurons: A General Framework for SO(3)-Equivariant Networks](https://mlsanity.com/paper/2104.12229/) (2021)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [Learning SO(3) Equivariant Representations with Spherical CNNs](https://mlsanity.com/paper/1711.06721/) (2017)
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://mlsanity.com/paper/2003.03164/) (2020)
- [PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors](https://mlsanity.com/paper/1808.10322/) (2018)
- [BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry](https://mlsanity.com/paper/2401.15563/) (2024)
- [BRepNet: A topological message passing system for solid models](https://mlsanity.com/paper/2104.00706/) (2021)
- [Rotation Invariant Convolutions for 3D Point Clouds Deep Learning](https://mlsanity.com/paper/1908.06297/) (2019)
- [What You See is What You Get: Exploiting Visibility for 3D Object Detection](https://mlsanity.com/paper/1912.04986/) (2019)
- [Rotation-Invariant Transformer for Point Cloud Matching](https://mlsanity.com/paper/2303.08231/) (2023)
- [A Rotation-Invariant Framework for Deep Point Cloud Analysis](https://mlsanity.com/paper/2003.07238/) (2020)
- [Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud](https://mlsanity.com/paper/2010.03318/) (2020)
- [HoLa: B-Rep Generation using a Holistic Latent Representation](https://mlsanity.com/paper/2504.14257/) (2025)
- [RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning](https://mlsanity.com/paper/2202.13094/) (2022)
- [RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials](https://mlsanity.com/paper/1901.01535/) (2019)
- [Global Context Aware Convolutions for 3D Point Cloud Understanding](https://mlsanity.com/paper/2008.02986/) (2020)
- [Self-Supervised Representation Learning for CAD](https://mlsanity.com/paper/2210.10807/) (2022)
- [DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometry](https://mlsanity.com/paper/2503.13110/) (2025)
- [Geometric Deep Learning for Computer-Aided Design: A Survey](https://mlsanity.com/paper/2402.17695/) (2024)
- [Bringing Attention to CAD: Boundary Representation Learning via Transformer](https://mlsanity.com/paper/2504.07134/) (2025)
- [NeuroNURBS: Learning Efficient Surface Representations for 3D Solids](https://mlsanity.com/paper/2411.10848/) (2024)
- [CAD 3D Model classification by Graph Neural Networks: A new approach based on STEP format](https://mlsanity.com/paper/2210.16815/) (2022)
- [Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis](https://mlsanity.com/paper/2403.11113/) (2024)

## Built on by (most cited first, 3 of 3)

- [CAD-feature enhanced machine learning for manufacturing effort estimation on sheet metal bending parts](https://mlsanity.com/paper/2605.12266/) (2026)
- [Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations](https://mlsanity.com/paper/2609.11573/) (2026)
- [CNCGEN: A Dataset and Framework for Machining Process Planning and Toolpath Generation from B-rep Models](https://mlsanity.com/paper/2609.39738/) (2026)

## Abstract (arXiv)

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.