PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration

TL;DR

PaRot is a novel neural network that achieves rotation invariance in 3D point cloud analysis by disentangling features and restoring pose information, leading to robust classification and segmentation.

Contribution

The paper introduces a patch-wise rotation-invariant network with a novel disentanglement and pose restoration mechanism for improved 3D shape analysis.

Findings

Achieves rotation-invariant features through disentanglement.

Performs competitively in rotated 3D classification and segmentation.

Introduces hierarchical feature aggregation and pose-aware propagation.

Abstract

Recent interest in point cloud analysis has led rapid progress in designing deep learning methods for 3D models. However, state-of-the-art models are not robust to rotations, which remains an unknown prior to real applications and harms the model performance. In this work, we introduce a novel Patch-wise Rotation-invariant network (PaRot), which achieves rotation invariance via feature disentanglement and produces consistent predictions for samples with arbitrary rotations. Specifically, we design a siamese training module which disentangles rotation invariance and equivariance from patches defined over different scales, e.g., the local geometry and global shape, via a pair of rotations. However, our disentangled invariant feature loses the intrinsic pose information of each patch. To solve this problem, we propose a rotation-invariant geometric relation to restore the relative pose with equivariant information for patches defined over different scales. Utilising the pose information, we propose a hierarchical module which implements intra-scale and inter-scale feature aggregation for 3D shape learning. Moreover, we introduce a pose-aware feature propagation process with the rotation-invariant relative pose information embedded. Experiments show that our disentanglement module extracts high-quality rotation-robust features and the proposed lightweight model achieves competitive results in rotated 3D object classification and part segmentation tasks. Our project page is released at: https://patchrot.github.io/.