Multi-scale Receptive Fields Graph Attention Network for Point Cloud Classification

TL;DR

This paper introduces MRFGAT, a multi-scale receptive fields graph attention network that effectively captures local fine features of point clouds, achieving state-of-the-art shape classification results.

Contribution

The paper proposes a novel multi-scale receptive fields graph attention network that enhances point cloud classification by focusing on local fine features with multi attention modules.

Findings

Achieves state-of-the-art accuracy on ModelNet10 and ModelNet40 datasets.

Effectively captures local fine features of point clouds.

Outperforms existing methods in shape classification tasks.

Abstract

Understanding the implication of point cloud is still challenging to achieve the goal of classification or segmentation due to the irregular and sparse structure of point cloud. As we have known, PointNet architecture as a ground-breaking work for point cloud which can learn efficiently shape features directly on unordered 3D point cloud and have achieved favorable performance. However, this model fail to consider the fine-grained semantic information of local structure for point cloud. Afterwards, many valuable works are proposed to enhance the performance of PointNet by means of semantic features of local patch for point cloud. In this paper, a multi-scale receptive fields graph attention network (named after MRFGAT) for point cloud classification is proposed. By focusing on the local fine features of point cloud and applying multi attention modules based on channel affinity, the learned feature map for our network can well capture the abundant features information of point cloud. The proposed MRFGAT architecture is tested on ModelNet10 and ModelNet40 datasets, and results show it achieves state-of-the-art performance in shape classification tasks.