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 a 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.

本文提出了一个新颖的 3D 物体检测框架，可直接处理 LiDAR 原始数据；利用稠密的测距图像，通过 2D 卷积方法高效处理数据，并使用新的 range-conditioned dilation (RCD) 层根据量测距离动态调整连续膨胀率，进一步提高了检测的精度。结合 3D bounding box 细化步骤能够更好地应对遮挡区域，在 Waymo Open 数据集上表现优异，创下了新的基准。