RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Driving

TL;DR

RefinedMPL introduces sparsification techniques for monocular PseudoLiDAR data, significantly improving 3D detection accuracy in autonomous driving while maintaining computational efficiency comparable to LiDAR-based methods.

Contribution

It proposes supervised and unsupervised sparsification schemes that enhance monocular 3D detection performance with minimal point data, achieving state-of-the-art results on KITTI dataset.

Findings

Improved detection accuracy for cars and pedestrians.

Achieved 54% relative improvement for pedestrians.

Reduced point cloud data to ~5% without performance loss.

Abstract

In this paper, we strive for solving the ambiguities arisen by the astoundingly high density of raw PseudoLiDAR for monocular 3D object detection for autonomous driving. Without much computational overhead, we propose a supervised and an unsupervised sparsification scheme of PseudoLiDAR prior to 3D detection. Both the strategies assist the standard 3D detector gain better performance over the raw PseudoLiDAR baseline using only ~5% of its points on the KITTI object detection benchmark, thus making our monocular framework and LiDAR-based counterparts computationally equivalent (Figure 1). Moreover, our architecture agnostic refinements provide state-of-the-art results on KITTI3D test set for "Car" and "Pedestrian" categories with 54% relative improvement for "Pedestrian". Finally, exploratory analysis is performed on the discrepancy between monocular and LiDAR-based 3D detection frameworks to guide future endeavours.