感觉是机器翻译,好多地方不通顺,凑合看看 原文名称:Complex-YOLO: An Euler-Region-Proposal for Real-time 3D Object Detection on Point Clouds原文地址:http://www.sohu.com/a/285118205_715754代码位置:https://github.com/Mandylove1993/complex-yolo(值得复现一下) 摘要.基于激光雷达的三维目标检测是自动驾驶的必然选择,因为它直接关
三维点云去噪无监督学习:ICCV2019论文分析 Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning 论文链接: http://openaccess.thecvf.com/content_ICCV_2019/papers/Hermosilla_Total_Denoising_Unsupervised_Learning_of_3D_Point_Cloud_Cleaning_ICCV_2019_paper.pdf 摘要
CVPR2020:点云分析中三维图形卷积网络中可变形核的学习 Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis 论文地址: https://openaccess.thecvf.com/content_CVPR_2020/papers/Lin_Convolution_in_the_Cloud_Learning_Deformab
CVPR2020:点云三维目标跟踪的点对盒网络(P2B) P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds 代码:https://github.com/HaozheQi/P2B 论文地址: https://openaccess.thecvf.com/content_CVPR_2020/papers/Qi_P2B_Point-to-Box_Network_for_3D_Object_Tracking_in_Point_
PointRCNN: 点云的3D目标生成与检测 PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud 论文地址:https://arxiv.org/abs/1812.04244 代码地址:https://github.com/sshaoshuai/PointRCNN 摘要 本文提出了一种基于点云的三维目标检测方法.整个框架由两个阶段组成:第一阶段用于自下而上的3D方案生成,第二阶段用于在标准坐标系中细化方案
CVPR2020:利用图像投票增强点云中的三维目标检测(ImVoteNet) ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes 论文地址: https://openaccess.thecvf.com/content_CVPR_2020/papers/Qi_ImVoteNet_Boosting_3D_Object_Detection_in_Point_Clouds_With_Image_CVPR_202