Hello and welcome
   All Categories
PointRCNN PointRCNN
PointRCNN Shi, Shaoshuai, Xiaogang Wang, and Hongsheng Li. “PointRCNN: 3D Object Proposal Generation and Detection from
2021-10-08 papers
Point Cloud PointRCNN
PointNet & PointNet++ PointNet & PointNet++
PointNet & PointNet++ Qi, Charles R., Hao Su, Kaichun Mo, and Leonidas J. Guibas. “PointNet: Deep Learning on Point
2021-10-08 papers
Point Cloud PointNet
PointPillars PointPillars
PointPillars note这篇文章也经常在其他文章中被提到，该网络特点就是具有非常快的推理速度。这篇文章的一个出发点之一，就是不想使用速度较慢的 3D convolution。这篇笔记比较潦草，但目的是梳理清楚模型的框架和流程 Ab
2021-10-08 papers
Point Cloud PointPillars
Point-GNN Point-GNN
Point-GNN note由于对于GNN没有过多的了解，并不能感受到GNN相对于CNN有极大的优势。相反的，在其中设计的很多结构，与使用CNN处理是相似的，最核心的观点就是捕捉到 (multi-scale) local feature，这
2021-10-08 papers
Point Cloud Point-GNN
PV-RCNN PV-RCNN
PV-RCNN Shi, Shaoshuai, Chaoxu Guo, Li Jiang, Zhe Wang, Jianping Shi, Xiaogang Wang, and Hongsheng Li. “PV-RCNN: Point-V
2021-10-08 papers
Point Cloud PV-RCNN
CenterPoint CenterPoint
CenterPoint Yin, Tianwei, Xingyi Zhou, and Philipp Krähenbühl. “Center-Based 3D Object Detection and Tracking.” ArXiv:20
2021-10-08 papers
Point Cloud CenterPoint
Faster RCNN Faster RCNN
Faster RCNN note本文总结自知乎链接https://zhuanlan.zhihu.com/p/31426458 整体思路Faster RCNN其实可以分为4个主要内容： Conv layers Faster RCNN首先使
2021-08-07 papers
Faster RCNN
CenterPoint 复现笔记 CenterPoint 复现笔记
CenterPoint 复现笔记Installation pytorch下载如果很慢，请采用镜像！ 下载cmake使用apt，但要更新下载源为阿里云，这样版本才够新 安装spconv时报错 The following packages
2021-07-25 papers
CenterPoint
2 / 2