Transformation-Equivariant 3D Object Detection for Autonomous Driving

by   Hai Wu, et al.
Xiamen University
Texas A&M University

3D object detection received increasing attention in autonomous driving recently. Objects in 3D scenes are distributed with diverse orientations. Ordinary detectors do not explicitly model the variations of rotation and reflection transformations. Consequently, large networks and extensive data augmentation are required for robust detection. Recent equivariant networks explicitly model the transformation variations by applying shared networks on multiple transformed point clouds, showing great potential in object geometry modeling. However, it is difficult to apply such networks to 3D object detection in autonomous driving due to its large computation cost and slow reasoning speed. In this work, we present TED, an efficient Transformation-Equivariant 3D Detector to overcome the computation cost and speed issues. TED first applies a sparse convolution backbone to extract multi-channel transformation-equivariant voxel features; and then aligns and aggregates these equivariant features into lightweight and compact representations for high-performance 3D object detection. On the highly competitive KITTI 3D car detection leaderboard, TED ranked 1st among all submissions with competitive efficiency.


A Survey of Robust 3D Object Detection Methods in Point Clouds

The purpose of this work is to review the state-of-the-art LiDAR-based 3...

The Impact of Different Backbone Architecture on Autonomous Vehicle Dataset

Object detection is a crucial component of autonomous driving, and many ...

SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving

Object detection (OD) is crucial to autonomous driving. Unknown objects ...

Pillar-based Object Detection for Autonomous Driving

We present a simple and flexible object detection framework optimized fo...

Mitigating Backdoor Attack Via Prerequisite Transformation

In recent years, with the successful application of DNN in fields such a...

Q-YOLOP: Quantization-aware You Only Look Once for Panoptic Driving Perception

In this work, we present an efficient and quantization-aware panoptic dr...

Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

This report presents our method which wins the nuScenes3D Detection Chal...

Please sign up or login with your details

Forgot password? Click here to reset