English

Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection

Computer Vision and Pattern Recognition 2021-01-25 v3 Machine Learning Robotics

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 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.

Keywords

Cite

@article{arxiv.2005.09927,
  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},
  journal= {arXiv preprint arXiv:2005.09927},
  year   = {2021}
}

Comments

CoRL 2020

R2 v1 2026-06-23T15:40:53.971Z