← Back to all news
arXiv Computer Vision By Heinrich Jiang, Hager Yasser Mohamed, Alexander Hitt, Valeriia Lomakina, Henning Jiang, Jennifer Jang

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

Read the original on arXiv Computer Vision →

The paper examines how boundary representation (B‑rep) encoders for CAD models fail to handle variations that do not change the underlying solid, such as different modeling operations or software export settings. By demonstrating that existing encoders collapse under these perturbations, the authors introduce the canonical region graph, a representation derived directly from the solid that is theoretically invariant to repartitioning and rigid motions. This new input format matches the best baseline on standard benchmarks and remains stable across all tested perturbations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

Hugging Face Trending Papers
Sep 10

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

Boundary representation (B‑rep) is the standard format for parametric 3D models in CAD systems, yet the same solid can be encoded by different B‑reps due to varying operations, kernel rebuilds, or export settings. Existing B‑rep encoders fail to handle these variations, collapsing on standard benchmarks and real‑world perturbations. The authors introduce the canonical region graph, an input representation derived directly from the solid, which offers theoretical invariance to repartitioning and rigid motions and performs as well as the best baseline while remaining stable across all tested perturbations.

benchmarks
More like this →
arXiv Machine Learning
Jun 3

CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization

arXiv:2605. 01171v2 Announce Type: replace-cross Abstract: Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for design and manufacturing, as existing CAD reconstruction and generation methods are largely restricted to difficult-to-edit formats like meshes or Breps or editable simple sketch-and-extrude pipelines and low-complexity datasets.

By Ghadi Nehme, Eamon Whalen, Faez Ahmed
multimodalbenchmarks
More like this →
arXiv AI
Jul 28

DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces

arXiv:2603. 05607v2 Announce Type: replace-cross Abstract: Computer-Aided Design (CAD) relies on structured and editable geometric representations, yet existing generative methods are constrained by small annotated datasets with explicit design histories or boundary representation (BRep) labels.

By Mohammad Sadil Khan, Muhammad Usama, Rolandos Alexandros Potamias, Didier Stricker, Muhammad Zeshan Afzal, Jiankang Deng, Ismail Elezi
llmsmultimodalbenchmarks
More like this →