Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection
Alex Bewley, Pei Sun, Thomas Mensink, Dragomir Anguelov, Cristian Sminchisescu
Abstract
This paper presents a novel 3D object detection framework that processes LiDAR data directly on its native representation: range images. Benefiting from the compactness of range images, 2D convolutions can efficiently process dense LiDAR data of the scene. To overcome scale sensitivity in this perspective view, a novel range-conditioned dilation (RCD) layer is proposed to dynamically adjust a continuous dilation rate as a function of the measured range. Furthermore, localized soft range gating combined with a 3D box-refinement stage improves robustness in occluded areas, and produces overall more accurate bounding box predictions. On the public large-scale Waymo Open Dataset, our method sets a new baseline for range-based 3D detection, outperforming multiview and voxel-based methods over all ranges with unparalleled performance at long range detection.
BibTeX
@inproceedings{corl2020_rangeconditioned,
title = {Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection},
author = {Alex Bewley and Pei Sun and Thomas Mensink and Dragomir Anguelov and Cristian Sminchisescu},
booktitle = {CoRL 2020},
year = {2020}
}