3DSSD: Point-based 3D Single Stage Object Detector

02/24/2020
by   Zetong Yang, et al.
17

Currently, there have been many kinds of voxel-based 3D single stage detectors, while point-based single stage methods are still underexplored. In this paper, we first present a lightweight and effective point-based 3D single stage object detector, named 3DSSD, achieving a good balance between accuracy and efficiency. In this paradigm, all upsampling layers and refinement stage, which are indispensable in all existing point-based methods, are abandoned to reduce the large computation cost. We novelly propose a fusion sampling strategy in downsampling process to make detection on less representative points feasible. A delicate box prediction network including a candidate generation layer, an anchor-free regression head with a 3D center-ness assignment strategy is designed to meet with our demand of accuracy and speed. Our paradigm is an elegant single stage anchor-free framework, showing great superiority to other existing methods. We evaluate 3DSSD on widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well, with inference speed more than 25 FPS, 2x faster than former state-of-the-art point-based methods.

READ FULL TEXT

page 5

page 8

research
11/27/2019

Soft Anchor-Point Object Detection

Recently, anchor-free detectors have shown great potential to outperform...
research
08/08/2021

Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud

Most of the existing single-stage and two-stage 3D object detectors are ...
research
07/22/2019

STD: Sparse-to-Dense 3D Object Detector for Point Cloud

We present a new two-stage 3D object detection framework, named sparse-t...
research
12/31/2020

Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection

Recent advances on 3D object detection heavily rely on how the 3D data a...
research
12/16/2021

AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds

There have been two streams in the 3D detection from point clouds: singl...
research
05/16/2022

PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

Real-time and high-performance 3D object detection is of critical import...
research
11/20/2017

Light-Head R-CNN: In Defense of Two-Stage Object Detector

In this paper, we first investigate why typical two-stage methods are no...

Please sign up or login with your details

Forgot password? Click here to reset