PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space: Difference between revisions

From statwiki
Jump to navigation Jump to search
No edit summary
Line 3: Line 3:




= Media =
[[File:point_cloud.png | 400px]]


= Review of PointNet =


[[File:pointnet_arch.png | 700px]]
[[File:pointnet_arch.png | 700px]]
= PointNet++ =
== Problem Statement ==
== Method ==


[[File:point_net++.png | 700px]]
[[File:point_net++.png | 700px]]


[[File:point_cloud.png | 400px]]
=== Sampling Layer ===


=== Grouping Layer ===


[[File:grouping.png | 300px]]
[[File:grouping.png | 300px]]
=== PointNet Layer ===
=== Robust Feature Learning under Non-Uniform Sampling Density ===
== Experiments ==


=Sources=
=Sources=

Revision as of 20:04, 16 March 2018

Introduction

This paper builds off of ideas from PointNet (Qi et al., 2017). PointNet is a deep neural network architecture that takes a point cloud as an input and has the ability to perform classification or point semantic segmentation. PointNet differs from other point cloud processing networks by directly taking the unordered points from the point cloud as input, instead of re-representing the point cloud by voxelization or 2D images.


Review of PointNet

PointNet++

Problem Statement

Method

Sampling Layer

Grouping Layer

PointNet Layer

Robust Feature Learning under Non-Uniform Sampling Density

Experiments

Sources

1. Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space, 2017

2. Charles R. Qi, Hao Su, Kaichun Mo, Leonidas J. Guibas. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation, 2017