Multi-view attention-convolution pooling network for 3D point cloud classification

doi:10.1007/s10489-021-02840-2

Multi-view attention-convolution pooling network for 3D point cloud classification

2021-10-30

9

OA

AI

DOI：10.1007/s10489-021-02840-2

Original

Original request for help

Save

Abstract

En 中文

Classifying 3D point clouds is an important and challenging task in computer vision. Currently, classification methods using multiple views lose characteristic or detail information during the representation or processing of views. For this reason, we propose a multi-view attention-convolution pooling network framework for 3D point cloud classification tasks. This framework uses Res2Net to extract the features from multiple 2D views. Our attention-convolution pooling method finds more useful information in the input data related to the current output, effectively solving the problem of feature information loss caused by feature representation and the detail information loss during dimensionality reduction. Finally, we obtain the probability distribution of the model to be classified using a full connection layer and the softmax function. The experimental results show that our framework achieves higher classification accuracy and better performance than other contemporary methods using the ModelNet40 dataset.

Keywords:

3D point cloud

Multi-view

Attention-convolution pooling

Point cloud classification

Multi-view attention-convolution pooling network for 3D point cloud classification

Abstract

Journal

Organization