RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Driving
This work addresses computational inefficiency and performance gaps in monocular 3D detection for autonomous driving, though it is incremental as it refines an existing PseudoLiDAR approach.
The paper tackles ambiguities from high-density raw PseudoLiDAR in monocular 3D object detection for autonomous driving, achieving state-of-the-art results on the KITTI benchmark with a 54% relative improvement for pedestrians using only about 5% of the points.
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.