Improving LiDAR 3D Object Detection via Range-based Point Cloud Density Optimization

TL;DR

This paper presents a simple, model-free pre-processing method that adjusts point cloud density based on distance to improve LiDAR 3D object detection performance without changing detector architecture.

Contribution

It introduces a novel range-based point cloud density adjustment technique using MCMC optimization, enhancing detection accuracy across different distances.

Findings

Improves detection performance on Waymo and ONCE datasets.

Enhances existing detectors without architecture modifications.

Demonstrates effectiveness of data-level adjustments over model changes.

Abstract

In recent years, much progress has been made in LiDAR-based 3D object detection mainly due to advances in detector architecture designs and availability of large-scale LiDAR datasets. Existing 3D object detectors tend to perform well on the point cloud regions closer to the LiDAR sensor as opposed to on regions that are farther away. In this paper, we investigate this problem from the data perspective instead of detector architecture design. We observe that there is a learning bias in detection models towards the dense objects near the sensor and show that the detection performance can be improved by simply manipulating the input point cloud density at different distance ranges without modifying the detector architecture and without data augmentation. We propose a model-free point cloud density adjustment pre-processing mechanism that uses iterative MCMC optimization to estimate optimal parameters for altering the point density at different distance ranges. We conduct experiments using four state-of-the-art LiDAR 3D object detectors on two public LiDAR datasets, namely Waymo and ONCE. Our results demonstrate that our range-based point cloud density manipulation technique can improve the performance of the existing detectors, which in turn could potentially inspire future detector designs.