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

09/23/2019
by   Can Chen, et al.
40

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.

READ FULL TEXT

page 1

page 3

page 4

research
09/28/2020

Multi-scale Receptive Fields Graph Attention Network for Point Cloud Classification

Understanding the implication of point cloud is still challenging to ach...
research
05/21/2019

GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud

Exploiting fine-grained semantic features on point cloud is still challe...
research
09/23/2021

Fast Point Voxel Convolution Neural Network with Selective Feature Fusion for Point Cloud Semantic Segmentation

We present a novel lightweight convolutional neural network for point cl...
research
03/12/2021

Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion

Given the prominence of current 3D sensors, a fine-grained analysis on t...
research
02/04/2022

Projection-based Point Convolution for Efficient Point Cloud Segmentation

Understanding point cloud has recently gained huge interests following t...
research
12/05/2021

Adaptive Channel Encoding for Point Cloud Analysis

Attention mechanism plays a more and more important role in point cloud ...
research
07/01/2019

Going Deeper with Point Networks

In this work, we introduce three generic point cloud processing blocks t...

Please sign up or login with your details

Forgot password? Click here to reset