Lidar Paper
文章平均质量分 92
FUTUREEEEEE
这个作者很懒,什么都没留下…
展开
-
论文解读:PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection目录PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object DetectionAbstraction:Method:1 PV-RCNN for Point Cloud Object Detection1.1 3D Voxel CNN for Effificient Feature Encoding and Pr原创 2021-10-05 11:21:56 · 865 阅读 · 0 评论 -
Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiD
SqueezeSegV2 论文解读Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud SqueezeSegV2 网络结构Contribution:1 提升雷达的抗噪能力 2 提出了使用合成数据训练的domain - shift pipeline抗噪能力显示环境下收集到的点云数据会存在缺失点的情况。缺失的点会引入drop原创 2021-09-29 20:45:45 · 254 阅读 · 0 评论 -
Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data
论文解读:Moving Object Segmentation in 3D LiDAR Data A Learning-based Approach Exploiting Sequential Data创新点AbstractRelated Work具体方法personal comment创新点在分割中引入了新的描述动态物体的特征dk,ild_{k, i}^{l}dk,il,dk,il=∣ri−rik→l∣rid_{k, i}^{l}=\frac{\left|r_{i}-r_{i}^{k \righta原创 2021-09-28 11:27:59 · 662 阅读 · 2 评论