SHReg: Strictly Rotation-Equivariant Point Cloud Registration via Spherical Harmonics

arXiv:2607.23096v1 Announce Type: new Abstract: Point cloud registration critically depends on local features that are both distinctive and robust to arbitrary 3D rotations. Existing learning-based methods typically approximate rotation invariance via fragile local reference frames or extensive data augmentation, providing only empirical invariance and often degrading under unseen rotational transformations. In this paper, we propose SHReg, a strictly rotation-equivariant point cloud registration framework grounded in the representation theory of SO(3). By representing local geometric features as irreducible representations of SO(3), SHReg guarantees exact equivariance under arbitrary rotations without relying on local reference frames. Built upon a spherical-harmonics-based equivariant backbone, SHReg jointly learns rotation-invariant descriptors for robust correspondence matching and rotation-equivariant features that preserve fine-grained orientation information. The preserved equivariant structure enables each correspondence to directly hypothesize a rigid transformation, reducing reliance on large-scale hypothesis sampling in conventional RANSAC-based pipelines and leading to improved robustness under challenging rotational variations. Extensive experiments on 3DMatch, 3DLoMatch, and KITTI demonstrate that SHReg consistently outperforms state-of-the-art methods in registration accuracy, particularly under large rotational perturbations.

Related

• GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusion
• PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
• 2L-LSH: A Locality-Sensitive Hash Function-Based Method For Rapid Point Cloud Indexing
• Real-Time LiDAR Gaussian Splatting SLAM

Source: arXiv cs.CV | 2026-07-28