Pointnet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

By Charles R. Qi et al

Published on June 7, 2017

Read the original document by opening this link in a new tab.

Table of Contents

1 Introduction
2 Problem Statement
3 Method
3.1 Review of PointNet [20]: A Universal Continuous Set Function Approximator
3.2 Hierarchical Point Set Feature Learning
3.3 Robust Feature Learning under Non-Uniform Sampling Density
3.4 Point Feature Propagation for Set Segmentation
4 Experiments
4.1 Point Set Classification in Euclidean Metric Space

Summary

Few prior works study deep learning on point sets. PointNet [20] is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to recognize fine-grained patterns and generalizability to complex scenes. In this work, we introduce a hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set. By exploiting metric space distances, our network is able to learn local features with increasing contextual scales...