cs.CVNov 2, 2026

Do We Still Need Rotation-Invariant Architectures? A Statistical Robustness Benchmark for Point Cloud Classification

Authors: Abdulla Nasir Chowdhury, Gulpi Qorik Oktagalu Pratamasunu, Kazuhiro Fukui

Organizations: University of Tsukuba

Abstract

A substantial line of work builds rotation invariance directly into point cloud architectures. We benchmark 10 architectures (PointNet, PointNet++, DGCNN, RIConv, RIConv++, RISurConv, PointMLP, PointTransformer, and the equivariant VN-PointNet and VN-DGCNN) across 5 domains under pose, noise, and occlusion, and analyze the results with confirmatory hypothesis tests rather than point estimates. The three rotation-invariant (RI) architectures achieve the best pose robustness but rank among the lowest on noise robustness in 4 of 5 domains. We ask whether this cost is intrinsic to invariance or specific to how invariance is obtained. We retrain all 10 architectures unchanged, with a simple invariance loss on the embedding and three training seeds each, and evaluate all models on the independently designed ModelNet40-C. Invariance training transfers narrowly but reliably. It improves exactly the corruption families its perturbations target wherever the baseline has headroom (mean occlusion +10.5, lidar +13.4 percentage points of accuracy). At matched training budget the best standard backbone and the best RI architecture end on par on unseen corruptions (within 2.5 percentage points in every seed), and invariance-trained RIConv++ is the most seed-stable top model. Once rotation augmentation is widened, standard backbones concede only a flat, angle-independent accuracy offset under full-sphere rotation. We release the benchmark along with a package for analyzing point cloud robustness and reproducing our results.

Figures & tables

Appendix figures & tables22 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Pointy - A Lightweight Transformer for Point Cloud Foundation Models

    Mar 11, 2026Konrad Szafer, Marek Kraft, Dominik BelterPoint Cloud Learning3D Foundation Models

  2. Structure-First Point Cloud Learning with Mapper Region Graphs

    Feb 5, 2026Jeongbin You, Donggun Kim, Sejun Park +1Point Cloud Corruption RobustnessPoint Cloud Classification

  3. Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness

    May 8, 2026Pedro Alonso, Chongshou Li, Tianrui LiPoint Cloud ClassificationAdversarial Robustness