Fast Hierarchical Neural Network for Feature Learning on Point Cloud

06/10/2019
by   Can Chen, et al.
0

The analyses relying on 3D point clouds are an utterly complex task, often involving million of points, but also requiring computationally efficient algorithms because of many real-time applications; e.g. autonomous vehicle. However, point clouds are intrinsically irregular and the points are sparsely distributed in a non-Euclidean space, which normally requires point-wise processing to achieve high performances. Although shared filter matrices and pooling layers in convolutional neural networks (CNNs) are capable of reducing the dimensionality of the problem and extracting high-level information simultaneously, grids and highly regular data format are required as input. In order to balance model performance and complexity, we introduce a novel neural network architecture exploiting local features from a manually subsampled point set. In our network, a recursive farthest point sampling method is firstly applied to efficiently cover the entire point set. Successively, we employ the k-nearest neighbours (knn) algorithm to gather local neighbourhood for each group of the subsampled points. Finally, a multiple layer perceptron (MLP) is applied on the subsampled points and edges that connect corresponding point and neighbours to extract local features. The architecture has been tested for both shape classification and segmentation using the ModelNet40 and ShapeNet part datasets, in order to show that the network achieves the best trade-off in terms of competitive performance when compared to other state-of-the-art algorithms.

READ FULL TEXT

page 1

page 3

page 5

research
03/30/2018

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

Deep neural networks have enjoyed remarkable success for various vision ...
research
04/07/2021

FatNet: A Feature-attentive Network for 3D Point Cloud Processing

The application of deep learning to 3D point clouds is challenging due t...
research
05/27/2020

PAI-Conv: Permutable Anisotropic Convolutional Networks for Learning on Point Clouds

Demand for efficient representation learning on point clouds is increasi...
research
10/24/2022

BoundED: Neural Boundary and Edge Detection in 3D Point Clouds via Local Neighborhood Statistics

Extracting high-level structural information from 3D point clouds is cha...
research
01/23/2018

PointCNN: Convolution On X-Transformed Points

We present a simple and general framework for feature learning from poin...
research
12/27/2019

Pointwise Attention-Based Atrous Convolutional Neural Networks

With the rapid progress of deep convolutional neural networks, in almost...
research
05/18/2019

SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud Processing

Deep neural networks have established themselves as the state-of-the-art...

Please sign up or login with your details

Forgot password? Click here to reset