3D点云目标检测语义分割深度学习SOTA方法代码论文数据集等.zip

# 3D-Point-Clouds 3D点云SOTA方法,代码,论文,数据集(点云目标检测&分割) * 如有疑问，微信：shuangyu_ai * 更多自动驾驶相关交流群，欢迎扫码加入：[自动驾驶感知(PCL/ROS+DL)：技术交流群汇总(新版)](https://mp.weixin.qq.com/s?__biz=MzI4OTY1MjA3Mg==&mid=2247486575&idx=1&sn=3145b7a5e9dda45595e1b51aa7e45171&chksm=ec2aa068db5d297efec6ba982d6a73d2170ef09a01130b7f44819b01de46b30f13644347dbf2#rd) 应同学建议，创建了星球 **【自动驾驶感知(PCL/ROS+DL)】** 专注于自动驾驶感知领域，包括传统方法(PCL点云库,ROS)和深度学习（目标检测+语义分割）方法。同时涉及Apollo，Autoware(基于ros2)，BEV感知，三维重建，SLAM(视觉+激光雷达) ，模型压缩（蒸馏+剪枝+量化等），自动驾驶模拟仿真，自动驾驶数据集标注&数据闭环等自动驾驶全栈技术，欢迎扫码二维码加入，一起登顶自动驾驶的高峰！  点云处理方法上主要包括两类方法 * 深度学习方法 [`python`] * 目标检测&语义分割&多目标跟踪（MOT） * [【202212done】目标检测最新论文实时更新](https://zhuanlan.zhihu.com/p/591349104) * [【202304done】语义分割最新论文实时更新](https://zhuanlan.zhihu.com/p/591349481) * 传统上基于规则的方法 [`c++`] * PCL:https://github.com/HuangCongQing/pcl-learning * ROS: https://github.com/HuangCongQing/ROS * Apollo笔记：https://github.com/HuangCongQing/apollo_note @[双愚](https://github.com/HuangCongQing) , 若fork或star请注明来源 ## TODO - [x] [【202212done】目标检测最新论文实时更新](https://zhuanlan.zhihu.com/p/591349104) - [x] [【202304done】语义分割最新论文实时更新](https://zhuanlan.zhihu.com/p/591349481) - [x] [【202209done】目标检测框架(pcdet+mmdetection3d+det3d+paddle3d)文章撰写](https://zhuanlan.zhihu.com/p/569189196?) - [x] [【202208done】数据集调研总结](https://zhuanlan.zhihu.com/p/551861727) - [ ] 数据集详细剖析：kitti&waymo&nuScenes - [ ] Apollo学习https://github.com/HuangCongQing/apollo_note ## 目录 #### 0 目标检测框架(pcdet+mmdetection3d+det3d+paddle3d) > [【202209done】目标检测框架(pcdet+mmdetection3d+det3d+paddle3d)文章撰写](https://zhuanlan.zhihu.com/p/569189196?) 代码注解笔记： 1. **pcdet:https://github.com/HuangCongQing/pcdet-note** 2. **mmdetection3d:https://github.com/HuangCongQing/mmdetection3d-note** 3. det3d: TODO 4. paddle3d: TODO #### 1 paper(code) * paperswithcode: https://paperswithcode.com/ #### 2 Datasets **[自动驾驶相关数据集调研总结【附下载地址】(更新ing)](https://zhuanlan.zhihu.com/p/551861727)** 数据集基本处理: [数据集标注文件处理](https://github.com/HuangCongQing/Python#%E7%82%B9%E4%BA%91%E7%9B%B8%E5%85%B3%E5%A4%84%E7%90%86) 部分数据下载脚本：https://github.com/HuangCongQing/download_3D_dataset #### 3 点云可视化 点云可视化笔记和代码：https://github.com/HuangCongQing/Point-Clouds-Visualization 3D点云可视化的库有很多，你的选择可能是： - pcl 点云可视化 [`c++`] - ROS topic可视化 [`c++`] [`python`] - open3D [`python`] - mayavi[`python`] - matplolib [`python`] #### 4 点云数据标注 数据标注工具总结：https://github.com/HuangCongQing/data-labeling-tools ## paper(code) ### 3D_Object_Detection - [x] [**>>>目标检测最新论文实时更新**](https://zhuanlan.zhihu.com/p/591349104) * One-stage * Two-stage #### One-stage > Voxel-Net、SECOND、PointPillars、HVNet、DOPS、Point-GNN、SA-SSD、3D-VID、3DSSD * Voxel-Net * SECOND * PointPillars * HVNet * DOPS * Point-GNN * SA-SSD * 3D-VID * 3DSSD #### Two-stage > F-pointNet、F-ConvNet、Point-RCNN、Part-A^2、PV-RCNN、Fast Point RCNN、TANet * F-pointNet * F-ConvNet * Point-RCNN * Part-A^2 * PV-RCNN * Fast Point RCNN * TANet ### 3D_Semantic_Segmentation - [x] [**>>>语义分割最新论文实时更新**](https://zhuanlan.zhihu.com/p/591349481) **PointNet** is proposed to learn per-point features using shared MLPs and global features using symmetrical pooling functions. Based on PointNet, a series of point-based networks have been proposed >Point-based Methods: these methods can be roughly divided into pointwise MLP methods, point convolution methods, RNN-based methods, and graph-based methods #### 1 pointwise MLP methods > PointNet++，PointSIFT，PointWeb，ShellNet，RandLA-Net PointNet++ PointSIFT PointWeb ShellNet RandLA-Net #### 2 point convolution methods > PointCNN PCCN A-CNN ConvPoint pointconv KPConv DPC InterpCNN * PointCNN * PCCN * A-CNN * ConvPoint * pointconv * KPConv * DPC * InterpCNN #### 3 RNN-based methods > G+RCU RSNet 3P-RNN DAR-Net * G+RCU * RSNet * 3P-RNN * DAR-Net #### 4 graph-based methods > DGCNN SPG SSP+SPG PyramNet GACNet PAG HDGCN HPEIN SPH3D-GCN DPAM * DGCNN * SPG * SSP+SPG * PyramNet * GACNet * PAG * HDGCN * HPEIN * SPH3D-GCN * DPAM ### 3D_Instance Segmentation ## Datasets ### 数据集下载 * **shell脚本下载方式: https://github.com/HuangCongQing/download_3D_dataset** - [https://hyper.ai/datasets](https://hyper.ai/datasets) - [https://www.graviti.cn/open-datasets](https://www.graviti.cn/open-datasets) > Graviti 收录了 400 多个高质量 CV 类数据集，覆盖无人驾驶、智慧零售、机器人等多种 AI 应用领域。举两个例子： > 文章> [https://bbs.cvmart.net/topics/3346](https://bbs.cvmart.net/topics/3346) - Google数据集搜索：[https://toolbox.google.com/datasetsearch](https://toolbox.google.com/datasetsearch) - Datahub，分享高质量数据集平台：[https://datahub.io/](https://datahub.io/) - 用于上传和查找数据集的机器学习数据集存储库：[https://www.webdoctx.com/www.mldata.org](https://www.webdoctx.com/www.mldata.org) - datafountain收集数据集：[https://www.datafountain.cn/dataSets](https://www.datafountain.cn/dataSets) - tinymind收集数据集：[https://www.tinymind.cn/sites#group_22](https://www.tinymind.cn/sites#group_22) 看到的一篇文章,里面有介绍很多数据集的：[世界上最有价值的不是石油而是数据(附数据资源下载链接)](https://mp.weixin.qq.com/s/Ao8SO9j2IPurl45Noy1dVw) - [https://www.graviti.cn/open-datasets](https://www.graviti.cn/open-datasets) ## Datasets数据集汇总 [https://github.com/Yochengliu/awesome-point-cloud-analysis#---datasets](https://github.com/Yochengliu/awesome-point-cloud-analysis#---datasets) - **[**[KITTI](http://www.cvlibs.net/datasets/kitti/)] The KITTI Vision Benchmark Suite. [`det.`]**常用 - [[ModelNet](http://modelnet.cs.princeton.edu/)] The Princeton ModelNet . [**`cls.`**] - [[ShapeNet](https://www.shapenet.org/)] A collaborative dataset between researchers at Princeton, Stanford and TTIC. [**`seg.`**] - [[PartNet](https://shapenet.org/download/parts)] The PartNet dataset provides fine grained part annotation of objects in ShapeNetCore. [**`seg.`**] - [[PartNet](http://kevinkaixu.net/projects/partnet.html)] PartNet benchmark from Nanjing University and National University of Defense Technology. [**`seg.`**] - **[**[**S3DIS**](http://buildingparser.stanford.edu/dataset.html#Download)**] The Stanford Large-Scale 3D Indoor Spaces Dataset. [`seg.`]**常用 - [[ScanNet](http://www.scan-net.org/)] Richly-annotated 3D Reconstructions of Indoor Scenes. [**`cls.`** **`seg.`**] - [[Stanford 3D](https://graphics.stanford.edu/data/3Dscanrep/)] The Stanford 3D Scanning Repository. [**`reg.`**] - [[UWA Dataset](http://staffhome.ecm.uwa.edu.au/~00053650/databases.html)] . [**`cls.`** **`seg.`** **`reg.`**] - [[Princeton Shape Benchmark](http://shape.cs.princeton.edu/benchmark/)] The Princeton Shape Benchmark. - [[SYDNEY URBAN OBJECTS DATASET](http://www.acfr.usyd.edu.au/papers/SydneyUrbanObjectsDataset.s