AI Paper Atlas

Research map / Point clouds / Point cloud classification

SO(3)-Equivariant Learning on CAD Boundary Representations

Matteo Ballegeer, Dries Benoit

NeurIPS 2026 · Point clouds › Point cloud classification · approach: Equivariant point cloud networks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an SO(3)-equivariant graph learning approach for CAD B-rep data that encodes surface geometry as equivariant features rather than rotation-sensitive scalars.

Problem

Existing B-rep CAD learning methods encode coordinates and normals as scalars, making them rotation-sensitive, while invariant alternatives based on per-face local frames lose a shared orientation reference needed to model inter-face directional relationships.

Approach

Uses SO(3)-equivariant learning on the B-rep geometric graph so that directional face-to-face relationships are captured under a shared global orientation reference, instead of scalar encodings or per-face local frames. Full method details are not available beyond the abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use SO(3)-equivariant CG message passing instead of FoV-Net's invariant local-frame messagesSO3brep · Fusion 360 segmentationaccuracy: 91.76 -> 95.11Improved
replace CG tensor product with non-equivariant message functions (ablation)SO3brep · Fusion 360 SO(3) testmIoU: 82.05 -> 61.89 (attention)Hurt
equivariant instead of invariant message passing at full training data (ablation)SO3brep · Fusion 360 / MFTRCADmIoU: +1.1 to +1.5 mIoU with 40% fewer parametersImproved
equivariant instead of invariant message passing with 100 training parts (ablation)SO3brep · MFTRCAD SO(3) testmIoU: 29.87 -> 43.01Improved
non-equivariant messages on aligned parts at full data (ablation)SO3brep · Fusion 360 original orientationaccuracy: 95.11 vs 95.31 (attention)No clear effect
remove node features (ablation)SO3brep · Fusion 360 segmentationaccuracy: -17.4 accuracy, -29.3 mIoU when removedImproved
add edge features (ablation)SO3brep · Fusion 360 segmentationmIoU: -3.1 accuracy, -9.6 mIoU when removedImproved
add attention aggregation instead of sum (ablation)SO3brep · Fusion 360 segmentationmIoU: -0.8 accuracy, -2.1 mIoU when removedImproved
increase maximum irrep degree from 0 to 1 and 2 (ablation)SO3brep · Fusion 360 segmentationmIoU: -1.0 mIoU at lmax=1, -3.2 at lmax=0Improved
add equivariance to a pose-sensitive classification datasetSO3brep · SolidLetters original orientationaccuracy: 97.36 (UV-Net) vs 97.03Hurt
SO3brep versus FoV-Net on BenDFMSO3brep · BenDFM SO(3) testaccuracy: 81.13 -> 81.68No clear effect
CG tensor products add computational costSO3brep · Fusion 360 inferenceinference time (ms): 8.3 -> 22.0 (vs FoV-Net)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy