Rotation Perturbation Robustness in Point Cloud Analysis: A Perspective of Manifold Distillation

TL;DR

This paper introduces a manifold distillation approach to enhance rotation perturbation robustness in point cloud analysis, improving accuracy and noise tolerance without coordinate transformation.

Contribution

It proposes a novel manifold distillation method using teacher-student networks to achieve rotation robustness in point cloud learning.

Findings

Improved classification accuracy by ~5% on Modelnet40 and ScanobjectNN datasets.

Enhanced segmentation performance with 7.36% and 4.82% mIoU gains on ShapeNet and S3DIS.

Demonstrated robustness against noise and outliers in experiments.

Abstract

Point cloud is often regarded as a discrete sampling of Riemannian manifold and plays a pivotal role in the 3D image interpretation. Particularly, rotation perturbation, an unexpected small change in rotation caused by various factors (like equipment offset, system instability, measurement errors and so on), can easily lead to the inferior results in point cloud learning tasks. However, classical point cloud learning methods are sensitive to rotation perturbation, and the existing networks with rotation robustness also have much room for improvements in terms of performance and noise tolerance. Given these, this paper remodels the point cloud from the perspective of manifold as well as designs a manifold distillation method to achieve the robustness of rotation perturbation without any coordinate transformation. In brief, during the training phase, we introduce a teacher network to learn the rotation robustness information and transfer this information to the student network through online distillation. In the inference phase, the student network directly utilizes the original 3D coordinate information to achieve the robustness of rotation perturbation. Experiments carried out on four different datasets verify the effectiveness of our method. Averagely, on the Modelnet40 and ScanobjectNN classification datasets with random rotation perturbations, our classification accuracy has respectively improved by 4.92% and 4.41%, compared to popular rotation-robust networks; on the ShapeNet and S3DIS segmentation datasets, compared to the rotation-robust networks, the improvements of mIoU are 7.36% and 4.82%, respectively. Besides, from the experimental results, the proposed algorithm also shows excellent performance in resisting noise and outliers.