Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations
The canonical region graph is proposed, an input representation whose nodes, features and coordinate frame are derived from the solid itself and show theoretical invariance guarantees on repartitioning and rigid motions and matches the strongest baseline on standard benchmarks, and is stable under every perturbation th...
Heinrich Jiang, Hager Yasser Mohamed, Alexander Hitt et al.
· 0 citations