Local region-learning modules for point cloud classification

TL;DR

This paper introduces two local region-learning modules that adaptively refine point cloud regions, significantly improving classification accuracy in 3D object recognition tasks.

Contribution

The paper proposes novel modules for dynamic local region adjustment in point cloud processing, integrated into existing architectures for enhanced performance.

Findings

Modules improve classification accuracy on ScanObjectNN dataset.

Modules are effective on ShapeNet 3D CAD models.

End-to-end training optimizes local region parameters.

Abstract

Data organization via forming local regions is an integral part of deep learning networks that process 3D point clouds in a hierarchical manner. At each level, the point cloud is sampled to extract representative points and these points are used to be centers of local regions. The organization of local regions is of considerable importance since it determines the location and size of the receptive field at a particular layer of feature aggregation. In this paper, we present two local region-learning modules: Center Shift Module to infer the appropriate shift for each center point, and Radius Update Module to alter the radius of each local region. The parameters of the modules are learned through optimizing the loss associated with the particular task within an end-to-end network. We present alternatives for these modules through various ways of modeling the interactions of the features and locations of 3D points in the point cloud. We integrated both modules independently and together to the PointNet++ and PointCNN object classification architectures, and demonstrated that the modules contributed to a significant increase in classification accuracy for the ScanObjectNN data set consisting of scans of real-world objects. Our further experiments on ShapeNet data set showed that the modules are also effective on 3D CAD models.