PyramNet: Point Cloud Pyramid Attention Network and Graph Embedding Module for Classification and Segmentation

TL;DR

PyramNet is a novel deep learning architecture for 3D point cloud classification and segmentation, utilizing graph embedding and pyramid attention modules to enhance local feature extraction and semantic understanding.

Contribution

The paper introduces two new operators, GEM and PAN, that improve local feature representation and semantic feature retention in point cloud analysis.

Findings

Effective on ModelNet40, ShapeNet, and S3DIS datasets.

Outperforms existing methods in classification and segmentation tasks.

Provides extensive evaluation confirming the model's robustness.

Abstract

With the tide of artificial intelligence, we try to apply deep learning to understand 3D data. Point cloud is an important 3D data structure, which can accurately and directly reflect the real world. In this paper, we propose a simple and effective network, which is named PyramNet, suites for point cloud object classification and semantic segmentation in 3D scene. We design two new operators: Graph Embedding Module(GEM) and Pyramid Attention Network(PAN). Specifically, GEM projects point cloud onto the graph and practices the covariance matrix to explore the relationship between points, so as to improve the local feature expression ability of the model. PAN assigns some strong semantic features to each point to retain fine geometric features as much as possible. Furthermore, we provide extensive evaluation and analysis for the effectiveness of PyramNet. Empirically, we evaluate our model on ModelNet40, ShapeNet and S3DIS.