【论文学习】PointNet++

Author：Charles R. Qi     Li Yi     Hao Su     Leonidas J. Guibas    Stanford University 

会议：Conference on Neural Information Processing Systems (NIPS) 2017

 

一、回顾PointNet

原理：

1、learn a spatial encoding of each point

2、aggregate all individual point features to a global point cloud signature（a single max pooling）

优点：an effective architecture to process an unordered set of points for semantic feature extraction

缺点：

1、does not capture local structure

2、没有考虑到不同的密度

方法：

point set {x1, x2, ..., xn}

γ and h are usually multi-layer perceptron (MLP) networks

h can be interpreted as the spatial encoding of a point

 

 

二、PointNet++

原理：<