Embracing Single Stride 3D Object Detector with Sparse Transformer

In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Over-looking this difference, many 3D detectors directly follow the common practice of 2D detectors, which downsample the feature maps...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 8448 - 8458
Main Authors: Fan, Lue, Pang, Ziqi, Zhang, Tianyuan, Wang, Yu-Xiong, Zhao, Hang, Wang, Feng, Wang, Naiyan, Zhang, Zhaoxiang
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2022
Subjects:
3D from multi-view and sensors; Navigation and autonomous driving
Detectors
Navigation
Object detection
Point cloud compression
Sensor phenomena and characterization
Three-dimensional displays
Transformers
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Over-looking this difference, many 3D detectors directly follow the common practice of 2D detectors, which downsample the feature maps even after quantizing the point clouds. In this paper, we start by rethinking how such multi-stride stereotype affects the LiDAR-based 3D object detectors. Our experiments point out that the downsampling operations bring few advantages, and lead to inevitable information loss. To remedy this issue, we propose Single-stride Sparse Transformer (SST) to maintain the original resolution from the beginning to the end of the network. Armed with transformers, our method addresses the problem of insufficient receptive field in single-stride architectures. It also cooperates well with the sparsity of point clouds and naturally avoids expensive computation. Eventually, our SST achieves state-of-the-art results on the large-scale Waymo Open Dataset. It is worth mentioning that our method can achieve exciting performance (83.8 LEVEL_1 AP on validation split) on small object (pedestrian) detection due to the characteristic of single stride. Our codes will be public soon.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.00827