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

From statwiki
Jump to: navigation, search
(Review of PointNet)
Line 3: Line 3:
  
  
[[File:point_cloud.png | 400px]]
+
[[File:point_cloud.png | 400px|thumb|center|Examples of point clouds]]]
  
 
= Review of PointNet =
 
= Review of PointNet =
Line 15: Line 15:
 
== Method ==
 
== Method ==
  
[[File:point_net++.png | 700px]]
+
[[File:point_net++.png | 700px|thumb|center|PointNet++ architecture]]]
  
 
=== Sampling Layer ===
 
=== Sampling Layer ===
Line 21: Line 21:
 
=== Grouping Layer ===
 
=== Grouping Layer ===
  
[[File:grouping.png | 300px]]
+
[[File:grouping.png | 300px|thumb|center|Example of the two ways to perform grouping]]]
  
 
=== PointNet Layer ===
 
=== PointNet Layer ===

Revision as of 19:07, 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.


Examples of point clouds
]

Review of PointNet

PointNet architecture
]

PointNet++

Problem Statement

Method

PointNet++ architecture
]

Sampling Layer

Grouping Layer

Example of the two ways to perform grouping
]

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