PointNorm: Normalization is All You Need for Point Cloud Analysis

by   Shen Zheng, et al.

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, those intricate hand-crafted model designs have led to poor inference latency and performance saturation in the last few years. In this paper, we point out that the classical sampling-grouping operations on the irregular point cloud cause learning difficulty for the subsequent MLP layers. To reduce the irregularity of the point cloud, we introduce a DualNorm module after the sampling-grouping operation. 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 PointNorm utilizes local mean and global standard deviation to benefit from both local and global features while maintaining a faithful inference speed. Experiments on point cloud classification show that we achieved state-of-the-art accuracy on ModelNet40 and ScanObjectNN datasets. We also generalize our model to point cloud part segmentation and demonstrate competitive performance on the ShapeNetPart dataset. Code is available at https://github.com/ShenZheng2000/PointNorm-for-Point-Cloud-Analysis.


page 3

page 8


PU-EdgeFormer: Edge Transformer for Dense Prediction in Point Cloud Upsampling

Despite the recent development of deep learning-based point cloud upsamp...

Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework

Point cloud analysis is challenging due to irregularity and unordered da...

PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloud

In order to retain more feature information of local areas on a point cl...

You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module

3D point-cloud-based perception is a challenging but crucial computer vi...

PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery

Point Cloud Sampling and Recovery (PCSR) is critical for massive real-ti...

Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities

Downsampling and feature extraction are essential procedures for 3D poin...

Equivariant Point Cloud Analysis via Learning Orientations for Message Passing

Equivariance has been a long-standing concern in various fields ranging ...

Please sign up or login with your details

Forgot password? Click here to reset