近期激光雷达点云的3D目标检测方法
作者 | 黄浴@知乎
编辑 | 3D视觉工坊
来源 | https://zhuanlan.zhihu.com/p/370650927
知圈 | 进“激光雷达社群”请加微信13636581676,备注激光
看到的一些近期激光雷达做目标检测的论文。
1 Offboard 3D Object Detection from Point Cloud Sequences, 3, 2021.
这是讲自动标注。
static object auto labeling
dynamic object auto labeling
2 SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud, 3, 2021.
预测前景点的空间形状,提取结构信息。
Spatial Information Enhancement Network (SIENet)
Network architecture of the HP(hybrid paradigm)-RPN
3 Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds, 4, 2021.
4 HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection, 4, 2021.
5 SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud, 4, 2021.
6 BEVDetNet: Bird’s Eye View LiDAR Point Cloud based Real-time 3D Object Detection for Autonomous Driving, 4, 2021.
点赞 评论 收藏