Fully Sparse 3D Object Detection

07/20/2022
by   Lue Fan, et al.
0

As the perception range of LiDAR increases, LiDAR-based 3D object detection becomes a dominant task in the long-range perception task of autonomous driving. The mainstream 3D object detectors usually build dense feature maps in the network backbone and prediction head. However, the computational and spatial costs on the dense feature map are quadratic to the perception range, which makes them hardly scale up to the long-range setting. To enable efficient long-range LiDAR-based object detection, we build a fully sparse 3D object detector (FSD). The computational and spatial cost of FSD is roughly linear to the number of points and independent of the perception range. FSD is built upon the general sparse voxel encoder and a novel sparse instance recognition (SIR) module. SIR first groups the points into instances and then applies instance-wise feature extraction and prediction. In this way, SIR resolves the issue of center feature missing, which hinders the design of the fully sparse architecture for all center-based or anchor-based detectors. Moreover, SIR avoids the time-consuming neighbor queries in previous point-based methods by grouping points into instances. We conduct extensive experiments on the large-scale Waymo Open Dataset to reveal the working mechanism of FSD, and state-of-the-art performance is reported. To demonstrate the superiority of FSD in long-range detection, we also conduct experiments on Argoverse 2 Dataset, which has a much larger perception range (200m) than Waymo Open Dataset (75m). On such a large perception range, FSD achieves state-of-the-art performance and is 2.4× faster than the dense counterpart.Codes will be released at https://github.com/TuSimple/SST.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/05/2023

Super Sparse 3D Object Detection

As the perception range of LiDAR expands, LiDAR-based 3D object detectio...
research
08/07/2023

FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels

LiDAR-based fully sparse architecture has garnered increasing attention....
research
01/16/2022

Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentation

Two major challenges of 3D LiDAR Panoptic Segmentation (PS) are that poi...
research
08/18/2023

Far3D: Expanding the Horizon for Surround-view 3D Object Detection

Recently 3D object detection from surround-view images has made notable ...
research
03/28/2023

LinK: Linear Kernel for LiDAR-based 3D Perception

Extending the success of 2D Large Kernel to 3D perception is challenging...
research
08/08/2023

An Empirical Analysis of Range for 3D Object Detection

LiDAR-based 3D detection plays a vital role in autonomous navigation. Su...
research
03/20/2023

VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking

3D object detectors usually rely on hand-crafted proxies, e.g., anchors ...

Please sign up or login with your details

Forgot password? Click here to reset