PointNorm: Dual Normalization is All You Need for Point Cloud Analysis

TL;DR

PointNorm introduces a dual normalization module for point cloud analysis that effectively addresses data irregularity, improving accuracy and efficiency across multiple 3D recognition and segmentation tasks.

Contribution

The paper proposes a novel DualNorm module with Point Normalization and Reverse Point Normalization to enhance point cloud processing efficiency and accuracy.

Findings

Achieved state-of-the-art accuracy on ModelNet40 classification.

Improved efficiency in point cloud analysis tasks.

Demonstrated effectiveness on multiple datasets including ShapeNetPart and S3DIS.

Abstract

Point cloud analysis is challenging due to the irregularity of the point cloud data structure. Existing works typically employ the ad-hoc sampling-grouping operation of PointNet++, followed by sophisticated local and/or global feature extractors for leveraging the 3D geometry of the point cloud. Unfortunately, the sampling-grouping operations do not address the point cloud's irregularity, whereas the intricate local and/or global feature extractors led to poor computational efficiency. In this paper, we introduce a novel DualNorm module after the sampling-grouping operation to effectively and efficiently address the irregularity issue. The DualNorm module consists of Point Normalization, which normalizes the grouped points to the sampled points, and Reverse Point Normalization, which normalizes the sampled points to the grouped points. The proposed framework, PointNorm, utilizes local mean and global standard deviation to benefit from both local and global features while maintaining a faithful inference speed. Experiments show that we achieved excellent accuracy and efficiency on ModelNet40 classification, ScanObjectNN classification, ShapeNetPart Part Segmentation, and S3DIS Semantic Segmentation. Code is available at https://github.com/ShenZheng2000/PointNorm-for-Point-Cloud-Analysis.