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 7: Line 7:
= Review of PointNet =
= Review of PointNet =
[[File:pointnet_arch.png | 700px]]
[[File:pointnet_arch.png | 700px|thumb|center|PointNet architecture]]]
= PointNet++ =
= PointNet++ =

Revision as of 19:06, 16 March 2018


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.

point cloud.png

Review of PointNet

PointNet architecture


Problem Statement


point net++.png

Sampling Layer

Grouping Layer


PointNet Layer

Robust Feature Learning under Non-Uniform Sampling Density



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