AI RESEARCH
FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting
arXiv CS.CV
•
ArXi:2602.24084v2 Announce Type: replace 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 $\mathbf{SO}(3)$ rotations. To address this, we