Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds

03/21/2022
by   Yifan Zhang, et al.
5

We study the problem of efficient object detection of 3D LiDAR point clouds. To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic random sampling or farthest point sampling to progressively downsample input point clouds, despite the fact that not all points are equally important to the task of object detection. In particular, the foreground points are inherently more important than background points for object detectors. Motivated by this, we propose a highly-efficient single-stage point-based 3D detector in this paper, termed IA-SSD. The key of our approach is to exploit two learnable, task-oriented, instance-aware downsampling strategies to hierarchically select the foreground points belonging to objects of interest. Additionally, we also introduce a contextual centroid perception module to further estimate precise instance centers. Finally, we build our IA-SSD following the encoder-only architecture for efficiency. Extensive experiments conducted on several large-scale detection benchmarks demonstrate the competitive performance of our IA-SSD. Thanks to the low memory footprint and a high degree of parallelism, it achieves a superior speed of 80+ frames-per-second on the KITTI dataset with a single RTX2080Ti GPU. The code is available at <https://github.com/yifanzhang713/IA-SSD>.

READ FULL TEXT

page 4

page 8

page 14

page 15

page 16

page 17

research
07/24/2023

PG-RCNN: Semantic Surface Point Generation for 3D Object Detection

One of the main challenges in LiDAR-based 3D object detection is that th...
research
11/15/2022

3D Cascade RCNN: High Quality Object Detection in Point Clouds

Recent progress on 2D object detection has featured Cascade RCNN, which ...
research
03/31/2023

IC-FPS: Instance-Centroid Faster Point Sampling Module for 3D Point-base Object Detection

3D object detection is one of the most important tasks in autonomous dri...
research
09/11/2020

A Density-Aware PointRCNN for 3D Objection Detection in Point Clouds

We present an improved version of PointRCNN for 3D object detection, in ...
research
10/10/2022

4D Unsupervised Object Discovery

Object discovery is a core task in computer vision. While fast progresse...
research
02/28/2022

Towards Class-agnostic Tracking Using Feature Decorrelation in Point Clouds

Single object tracking in point clouds has been attracting more and more...
research
12/11/2022

Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection

The dominant multi-camera 3D detection paradigm is based on explicit 3D ...

Please sign up or login with your details

Forgot password? Click here to reset