PapersSelected

Canonical Inputs for Neural Networks on CAD Boundary Representations

Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations

Why we picked it

For anyone working with AI and CAD, this paper provides a new method to make neural networks more robust to variations in 3D model data.

This paper addresses a problem in AI for CAD: existing B-rep encoders are not robust to variations in the same solid's representation. The authors propose a new input representation called the canonical region graph that is theoretically invariant to repartitioning and rigid motions, making it stable under perturbations and matching the strongest baseline on standard benchmarks.

Original · arXiv cs.AI

Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations

Boundary representation (B-rep) is the standard format used by modern CAD systems for parametric 3D models. It turns out, the exact same solid can be represented by different B-reps: for example, two engineers using different operations, a geometry kernel rebuilding the file, and an export setting repartitioning faces will lead to different B-reps even though the underlying solid remains the same. We show that existing B-rep encoders are not robust to variation in the B-rep with the same solid on perturbations applied to standard benchmarks, naturally occurring variations inherent to CAD software, and differences in how designers model the same part via a human dataset we created in FreeCAD. The performance of popular B-rep encoders often collapses catastrophically. We propose the canonical region graph, 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. It matches the strongest baseline on standard benchmarks, and is stable under every perturbation we test.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include CAD, B-rep, neural networks, model stability.

Source attribution: curated from arXiv cs.AI (@Heinrich Jiang, Hager Yasser Mohamed, Alexander Hitt, Valeriia Lomakina, Henning Jiang, Jennifer Jang).