GraVoS: Voxel Selection for 3D Point-Cloud Detection

TL;DR

This paper introduces GraVoS, a voxel selection method that improves 3D point-cloud detection by removing uninformative voxels to address data imbalance issues.

Contribution

Proposes a novel voxel selection approach that enhances 3D detection performance by addressing scene and class imbalance without adding data.

Findings

Improves detection accuracy across multiple 3D detectors

Effectively addresses foreground-background and class imbalance

Generalizable to various voxel-based detection methods

Abstract

3D object detection within large 3D scenes is challenging not only due to the sparsity and irregularity of 3D point clouds, but also due to both the extreme foreground-background scene imbalance and class imbalance. A common approach is to add ground-truth objects from other scenes. Differently, we propose to modify the scenes by removing elements (voxels), rather than adding ones. Our approach selects the "meaningful" voxels, in a manner that addresses both types of dataset imbalance. The approach is general and can be applied to any voxel-based detector, yet the meaningfulness of a voxel is network-dependent. Our voxel selection is shown to improve the performance of several prominent 3D detection methods.