- 博客(12)
- 资源 (1)
- 收藏
- 关注
RSS订阅
原创 3D物体检测(二)
title: 3D物体检测(二)date: 2020-02-22 17:09:40categories:3D物体检测tags:3D物体检测点云总结一下在bilibili上看到的基于点云场景的三维物体检测算法及应用,是香港中文大学博士生所作报告有兴趣的也可以去看看这个视频。这一部分主要总结一下报告主要的三个论文:PointRCNN、Part-A^2、PV-RCNN想看更多相...
2020-02-24 12:41:28
822
1
原创 点云基于图论的处理方法
本系列是按照bilibili上刘永成博士的分享课的论文笔记，主要针对点云基于图论的处理方法。这一部分主要讲解的方法包括：DGCNN、RGCNN、Spectral Graph Convolution、DeepGCNs个人博客链接: https://harrylin-hyl.github.ioDGCNN (TOG 2019)DGCNN: Dynamic Graph CNN for Learni...
2020-02-19 20:27:54
1926
1
原创 语义分割中的损失
语义分割中的损失loss list:CEBCEWCEFocal lossDice lossIOU lossTversky loss敏感性–特异性 lossGeneralized Dice lossBCE + Dice lossDice + Focal lossExponential Logarithmic loss以上部分有一篇博客讲得比较清楚：原文博客链接: (h...
2019-12-02 22:19:25
2429
原创 3D 目标检测 阅读笔记（二）
ImVoteNet(CVPR 2020)点云数据和图像数据的互补性表达：Additionally,images can cover “blind regions” of active depth sensors which often occur due to reflective surfaces. On the other hand, images are limited in the 3D detection task as they lack absolute measures of objec
2020-09-10 15:43:10
470
原创 FixMatch Simplifying Semi-Supervised Learning with Consistency and Confidence
FixMatch Simplifying Semi-Supervised Learning with Consistency and Confidence作者：Kihyuk Sohn∗ David Berthelot∗Chun-Liang Li Zizhao Zhang Nicholas Carlini Ekin D. Cubuk Alex Kurakin Han Zhang Colin Raffel机构：Google Research出处：arXiv:2001.07685写作技巧w
2020-08-23 16:50:38
1359
原创 SESS: Self-Ensembling Semi-Supervised 3D Object Detection
SESS: Self-Ensembling Semi-Supervised 3D Object Detection作者：Na Zhao Tat-Seng Chua Gim Hee Lee机构：Deaprtment of Computer Science, National University of Singapore出处：CVPR 2020 Oral代码：https://github.com/Na-Z/sess写作笔记alternative：选择robotics communitie
2020-08-18 21:30:03
683
原创 Structure Aware Single-stage 3D Object Detection from Point Cloud
Structure Aware Single-stage 3D Object Detection from Point Cloud作者：Chenhang He, Hui Zeng, Jianqiang Huang, Xian-Sheng Hua, Lei Zhang机构：The Hong Kong Polytechnic University, DAMO Academy, Alibaba Group出处： CVPR 2020主要贡献提出一种结构感知的单阶段网络，通过可丢弃的辅助网络和辅助损失
2020-08-14 22:38:48
355
原创 Pseudo-LiDAR from Visual Depth Estimation
Pseudo-LiDAR from Visual Depth Estimation:Bridging the Gap in 3D Object Detection for Autonomous Driving作者：Yan Wang, Wei-Lun Chao, Divyansh Garg, Bharath Hariharan, Mark Campbell, and Kilian Q. Weinberger机构：Cornell University, Ithaca, NY出处：CVPR 2019主
2020-08-13 19:41:18
439
原创 Task-Aware Monocular Depth Estimation for 3D Object Detection
Task-Aware Monocular Depth Estimation for 3D Object Detection作者：XinlongWang, Wei Yin, Tao Kong, Yuning Jiang, Lei Li, Chunhua Shen机构：The University of Adelaide, Australia、Bytedance AI Lab出处：AAAI 2020主要贡献分析前景背景对深度估计分别的影响，将两者区别对待提出ForeSeE模块在效果上将For
2020-08-13 15:11:22
624
原创 3D物体检测(一)
title: 3D物体检测(一)date: 2020-02-21 16:40:40categories:3D物体检测tags:3D物体检测点云总结一下在bilibili上看到的基于点云场景的三维物体检测算法及应用,有兴趣的也可以去看看这个视频。这一部分主要总结一下，结合雷达点云数据和相机采集的二维图像数据的方法。主要包括: MV3D-Net、F-PointNetMV3...
2020-02-24 12:36:11
3396
原创 语义分割中的损失
语义分割中的损失Lov´asz-SoftmaxlossSubmodularity and the Lovász extension推荐阅读：https://sudeepraja.github.io/Submodular/submodularitysubmodular实际上就对“边际效用递减”这个说法的形式化。[n]={1,2,..,n}[n]=\left\{1,2,..,n \r...
2019-11-27 21:49:20
1324
3D物体检测(一).md
2020-02-24
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人