RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection

by   Lue Fan, et al.

In this paper, we propose an anchor-free single-stage LiDAR-based 3D object detector – RangeDet. The most notable difference with previous works is that our method is purely based on the range view representation. Compared with the commonly used voxelized or Bird's Eye View (BEV) representations, the range view representation is more compact and without quantization error. Although there are works adopting it for semantic segmentation, its performance in object detection is largely behind voxelized or BEV counterparts. We first analyze the existing range-view-based methods and find two issues overlooked by previous works: 1) the scale variation between nearby and far away objects; 2) the inconsistency between the 2D range image coordinates used in feature extraction and the 3D Cartesian coordinates used in output. Then we deliberately design three components to address these issues in our RangeDet. We test our RangeDet in the large-scale Waymo Open Dataset (WOD). Our best model achieves 72.9/75.9/65.8 3D AP on vehicle/pedestrian/cyclist. These results outperform other range-view-based methods by a large margin ( 20 3D AP in vehicle detection), and are overall comparable with the state-of-the-art multi-view-based methods. Codes will be public.


page 1

page 6


Redemption from Range-view for Accurate 3D Object Detection

Most recent approaches for 3D object detection predominantly rely on poi...

RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representation

We present RangeRCNN, a novel and effective 3D object detection framewor...

A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation

3D object detection using LiDAR data is an indispensable component for a...

Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle

It is difficult to perform 3D reconstruction from on-vehicle gathered vi...

BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye View

On-board 3D object detection in autonomous vehicles often relies on geom...

Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection

This paper presents a novel 3D object detection framework that processes...

M^2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation

In this paper, we propose M^2BEV, a unified framework that jointly perfo...

Please sign up or login with your details

Forgot password? Click here to reset