Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutions

TL;DR

This paper introduces ShufflePointNet, a deep-wide neural network using group convolutions and channel shuffling to efficiently analyze point clouds, achieving high accuracy with reduced complexity.

Contribution

The paper proposes a novel deep-wide neural network architecture that employs group convolutions and channel shuffling for efficient point cloud analysis, improving performance and reducing redundancy.

Findings

Outperforms state-of-the-art methods on shape classification and segmentation tasks.

Reduces computational complexity while maintaining high accuracy.

Demonstrates effectiveness across multiple large-scale datasets.

Abstract

In order to achieve better performance for point cloud analysis, many researchers apply deeper neural networks using stacked Multi-Layer-Perceptron (MLP) convolutions over irregular point cloud. However, applying dense MLP convolutions over large amount of points (e.g. autonomous driving application) leads to inefficiency in memory and computation. To achieve high performance but less complexity, we propose a deep-wide neural network, called ShufflePointNet, to exploit fine-grained local features and reduce redundancy in parallel using group convolution and channel shuffle operation. Unlike conventional operation that directly applies MLPs on high-dimensional features of point cloud, our model goes wider by splitting features into groups in advance, and each group with certain smaller depth is only responsible for respective MLP operation, which can reduce complexity and allows to encode more useful information. Meanwhile, we connect communication between groups by shuffling groups in feature channel to capture fine-grained features. We claim that, multi-branch method for wider neural networks is also beneficial to feature extraction for point cloud. We present extensive experiments for shape classification task on ModelNet40 dataset and semantic segmentation task on large scale datasets ShapeNet part, S3DIS and KITTI. We further perform ablation study and compare our model to other state-of-the-art algorithms in terms of complexity and accuracy.