Current LiDAR-only 3D detection methods inevitably suffer from the sparsity of point clouds.
Many multi-modal methods are proposed to alleviate this issue, while different …

There have been two streams in the 3D detection from point clouds: single-stage methods
and two-stage methods. While the former is more computationally efficient, the latter usually …

Recent progress on multi-modal 3D object detection has featured BEV (Bird-Eye-View)
based fusion, which effectively unifies both LiDAR point clouds and camera images in a …

Currently, anchor-free single-stage 3D object detection methods based on point clouds have
attracted extensive attention due to their high efficiency. It is crucial to enhance the ability of …

One-stage 3-D object detection, known for its simplicity and high-speed inference, is
attracting increasing attention in autonomous driving scenarios. However, current one-stage …

In this technical report, we introduce our submission to the Waymo 3D Detection
leaderboard. Our network is based on the Centerpoint architecture, but with significant …

随着自动驾驶技术的发展, 对车辆环境的3D 感知要求越来越高, 而多传感器融合可以很好的满足
这一要求. 针对目前融合技术中存在的网络设计不系统, 信息丢失过大和融合策略粗糙问题 …

In this report, we present our winning solution to the 3D object detection of the SSLAD2021
Challenge at ICCV 2021. We propose a simple yet effective one-stage detector based on the …