STEP-Parts: Geometric Partitioning of Boundary Representations for Large-Scale CAD Processing

TL;DR

STEP-Parts is a deterministic pipeline that extracts stable, instance-level geometric partitions directly from raw STEP B-Reps, enhancing CAD analysis and learning tasks.

Contribution

It introduces a novel method for partitioning B-Reps based on primitive types and topology, retaining stability under tessellation changes.

Findings

Processed 180,000 models in under six hours on a consumer CPU.

Partition boundaries are stable under tessellation variations.

Serves as a geometric reference and supervision source for downstream learning.

Abstract

Many CAD learning pipelines discretize Boundary Representations (B-Reps) into triangle meshes, discarding analytic surface structure and topological adjacency and thereby weakening consistent instance-level analysis. We present STEP-Parts, a deterministic CAD-to-supervision toolchain that extracts geometric instance partitions directly from raw STEP B-Reps and transfers them to tessellated carriers through retained source-face correspondence, yielding instance labels and metadata for downstream learning and evaluation. The construction merges adjacent B-Rep faces only when they share the same analytic primitive type and satisfy a near-tangent continuity criterion. On ABC, same-primitive dihedral angles are strongly bimodal, yielding a threshold-insensitive low-angle regime for part extraction. Because the partition is defined on intrinsic B-Rep topology rather than on a particular triangulation, the resulting boundaries remain stable under changes in tessellation. Applied to the DeepCAD subset of ABC, the pipeline processes approximately 180{,}000 models in under six hours on a consumer CPU. We release code and precomputed labels, and show that STEP-Parts serves both as a tessellation-robust geometric reference and as a useful supervision source in two downstream probes: an implicit reconstruction--segmentation network and a dataset-level point-based backbone.