PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space: Difference between revisions
No edit summary |
|||
Line 24: | Line 24: | ||
= PointNet++ = | = PointNet++ = | ||
The motivation for PointNet++ is that PointNet does not capture local, fine-grained details. Since PointNet performs a max pool layer over all of its points, information such as the local interaction between points is lost. | |||
== Problem Statement == | == Problem Statement == | ||
There is a metric space <math> X = (M,d) </math> where <math>d</math> is the metric from a Euclidean space <math>\pmb{\mathbb{R}}^n</math> and <math> M \subseteq \pmb{\mathbb{R}}^n </math> is the set of points. The goal is to learn a function that takes <math>X</math> as the input as outputs a a class or per point label to each member of <math>M</math>. | |||
== Method == | == Method == | ||
[[File:point_net++.png | 700px|thumb|center|PointNet++ architecture | The PointNet++ architecture is shown below. | ||
[[File:point_net++.png | 700px|thumb|center|PointNet++ architecture]] | |||
=== Sampling Layer === | === Sampling Layer === | ||
Line 35: | Line 41: | ||
=== Grouping Layer === | === Grouping Layer === | ||
[[File:grouping.png | 300px|thumb|center|Example of the two ways to perform grouping | [[File:grouping.png | 300px|thumb|center|Example of the two ways to perform grouping]] | ||
=== PointNet Layer === | === PointNet Layer === |
Revision as of 23:08, 16 March 2018
Introduction
This paper builds off of ideas from PointNet (Qi et al., 2017). The name PointNet is derived from the network's input - a point cloud. A point cloud is a set of three dimensional points that each have coordinates [math]\displaystyle{ (x,y,z) }[/math]. These coordinates usually represent the surface of an object. For example, a point cloud describing the shape of a torus is shown below.
Processing point clouds is important in applications such as autonomous driving where point clouds are collected from an onboard LiDAR sensor. These point clouds can then be used for object detection. However, point clouds are challenging to process because:
- They are unordered. If [math]\displaystyle{ N }[/math] is the number of points in a point cloud, then there are [math]\displaystyle{ N! }[/math] permutations that the point cloud can be represented.
- The spatial arrangement of the points contains useful information, thus it needs to be encoded.
- The function processing the point cloud needs to be invariant to transformations such as rotation and translations of all points.
Previously, typical point cloud processing methods handled the challenges of point clouds by transforming the data with a 3D voxel grid or by representing the point cloud with multiple 2D images. When PointNet was introduced, it was novel because it directly took points as its input. PointNet++ improves on PointNet by using a hierarchical method to better capture local structures of the point cloud.
Review of PointNet
The PointNet architecture is shown below. The input of the network is [math]\displaystyle{ n }[/math] points, which each have [math]\displaystyle{ (x,y,z) }[/math] coordinates. Each point processed individually through a multi-layer perceptron (MLP). This network creates an encoding for each point; in the diagram, each point is represented by a 1024 dimension vector. Then, using a max pool layer a vector is created, that represents the "global signature" of a point cloud. If classification is the task, this global signature is processed by another MLP to compute the classification scores. If segmentation is the task, this global signature is appended to to each point from the "nx64" layer, and these points are processed by a MLP to compute a semantic category score for each point.
The core idea of the network is to learn a symmetric function on transformed points. Through the T-Nets and the MLP network, a transformation is learned with the hopes of making points invariant to point cloud transformations. Learning a symmetric function solves the challenge imposed by having unordered points; a symmetric function will produce the same value no matter the order of the input. This symmetric function is represented by the max pool layer.
PointNet++
The motivation for PointNet++ is that PointNet does not capture local, fine-grained details. Since PointNet performs a max pool layer over all of its points, information such as the local interaction between points is lost.
Problem Statement
There is a metric space [math]\displaystyle{ X = (M,d) }[/math] where [math]\displaystyle{ d }[/math] is the metric from a Euclidean space [math]\displaystyle{ \pmb{\mathbb{R}}^n }[/math] and [math]\displaystyle{ M \subseteq \pmb{\mathbb{R}}^n }[/math] is the set of points. The goal is to learn a function that takes [math]\displaystyle{ X }[/math] as the input as outputs a a class or per point label to each member of [math]\displaystyle{ M }[/math].
Method
The PointNet++ architecture is shown below.
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