{"id":13712282,"url":"https://github.com/TianhaoFu/Awesome-3D-Object-Detection","last_synced_at":"2025-05-06T21:33:43.477Z","repository":{"id":38615198,"uuid":"464710584","full_name":"TianhaoFu/Awesome-3D-Object-Detection","owner":"TianhaoFu","description":"Papers, code and datasets about deep learning for 3D Object Detection.","archived":false,"fork":false,"pushed_at":"2023-12-01T03:21:22.000Z","size":1938,"stargazers_count":632,"open_issues_count":1,"forks_count":54,"subscribers_count":18,"default_branch":"main","last_synced_at":"2025-05-04T22:01:59.997Z","etag":null,"topics":["3d-representation","autonomous-driving","computer-vision","cvpr","cvpr2020","cvpr2021","cvpr2022","deep-learning","deep-neural-networks","machine-learning","object-detection","paper","papers","point-cloud","point-cloud-detection","point-cloud-processing","point-clouds","python","reading-list","study-notes"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/TianhaoFu.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2022-03-01T02:04:36.000Z","updated_at":"2025-05-03T13:45:36.000Z","dependencies_parsed_at":"2024-01-13T19:35:47.949Z","dependency_job_id":"a4bb0d10-053a-4e1e-8e17-147eedb82389","html_url":"https://github.com/TianhaoFu/Awesome-3D-Object-Detection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TianhaoFu%2FAwesome-3D-Object-Detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TianhaoFu%2FAwesome-3D-Object-Detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TianhaoFu%2FAwesome-3D-Object-Detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TianhaoFu%2FAwesome-3D-Object-Detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TianhaoFu","download_url":"https://codeload.github.com/TianhaoFu/Awesome-3D-Object-Detection/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252772502,"owners_count":21801934,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["3d-representation","autonomous-driving","computer-vision","cvpr","cvpr2020","cvpr2021","cvpr2022","deep-learning","deep-neural-networks","machine-learning","object-detection","paper","papers","point-cloud","point-cloud-detection","point-cloud-processing","point-clouds","python","reading-list","study-notes"],"created_at":"2024-08-02T23:01:16.666Z","updated_at":"2025-05-06T21:33:42.742Z","avatar_url":"https://github.com/TianhaoFu.png","language":null,"funding_links":[],"categories":["Others","Summary","Other Lists"],"sub_categories":["TeX Lists"],"readme":"[![Maintenance](https://img.shields.io/badge/Maintained%3F-YES-green.svg)]()\n[![Ask Me Anything !](https://img.shields.io/badge/Ask%20me-anything-1abc9c.svg)](https://GitHub.com/Naereen/ama)\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n[![GitHub license](https://img.shields.io/github/license/HuaizhengZhang/Awesome-System-for-Machine-Learning.svg?color=blue)](https://github.com/HuaizhengZhang/Awesome-System-for-Machine-Learning/blob/master/LICENSE)\n\n\n# Awesome-3D-Object-Detection\nA curated list of research in 3D Object Detection(**Lidar-based Method**). \n\nYou are very welcome to pull request to update this list. :smiley:   \n![3D Object Detection](https://github.com/TianhaoFu/Awesome-3D-Object-Detection/blob/main/3d.png)\n\n## Dataset\n- [KITTI Dataset](http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d)\n  - 3,712 training samples\n  - 3,769 validation samples\n  - 7,518 testing samples\n\n- [nuScenes Dataset](https://www.nuscenes.org/)\n  - 28k training samples\n  - 6k validation samples\n  - 6k testing samples\n\n- [Lyft Dataset](https://level-5.global/data/perception/)\n- [Waymo Open Dataset](https://waymo.com/open/download/)\n  - 798 training sequences with around 158, 361 LiDAR samples\n  - 202 validation sequences with 40, 077 LiDAR samples.\n\n## Top conference \u0026 workshop\n### Conferene\n- Conference on Computer Vision and Pattern Recognition(CVPR)\n- International Conference on Computer Vision(ICCV)\n- European Conference on Computer Vision(ECCV)\n### Workshop\n- CVPR 2019 Workshop on Autonomous Driving([nuScenes 3D detection](http://cvpr2019.wad.vision/))\n- CVPR 2020 Workshop on Autonomous Driving([BDD1k 3D tracking](http://cvpr2020.wad.vision/))\n- CVPR 2021 Workshop on Autonomous Driving([waymo 3D detection](http://cvpr2021.wad.vision/))\n- CVPR 2022 Workshop on Autonomous Driving([waymo 3D detection](http://cvpr2022.wad.vision/))\n- [CVPR 2021 Workshop on 3D Vision and Robotics](https://sites.google.com/view/cvpr2021-3d-vision-robotics)\n- [CVPR 2021 Workshop on 3D Scene Understanding for Vision, Graphics, and Robotics](https://scene-understanding.com/)\n\n- [ICCV 2019 Workshop on Autonomous Driving](http://wad.ai/)\n- [ICCV 2021 Workshop on Autonomous Vehicle Vision (AVVision)](https://avvision.xyz/iccv21/), [note](https://openaccess.thecvf.com/content/ICCV2021W/AVVision/papers/Fan_Autonomous_Vehicle_Vision_2021_ICCV_Workshop_Summary_ICCVW_2021_paper.pdf)\n- [ICCV 2021 Workshop SSLAD Track 2 - 3D Object Detection](https://competitions.codalab.org/competitions/33236#learn_the_details)\n- [ECCV 2020 Workshop on Commands for Autonomous Vehicles](https://c4av-2020.github.io/)\n- [ECCV 2020 Workshop on Perception for Autonomous Driving](https://sites.google.com/view/pad2020)\n## Paper (Lidar-based method)\n- End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds [paper](https://github.com/Tom-Hardy-3D-Vision-Workshop/awesome-3D-object-detection/blob/master)\n- Vehicle Detection from 3D Lidar Using Fully Convolutional Network(baidu) [paper](https://arxiv.org/abs/1608.07916)\n- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection [paper](https://arxiv.org/pdf/1711.06396.pdf)\n- Object Detection and Classification in Occupancy Grid Maps using Deep Convolutional Networks [paper](https://arxiv.org/pdf/1805.08689.pdf)\n- RT3D: Real-Time 3-D Vehicle Detection in LiDAR Point Cloud for Autonomous Driving [paper](https://www.onacademic.com/detail/journal_1000040467923610_4dfe.html)\n- BirdNet: a 3D Object Detection Framework from LiDAR information [paper](https://arxiv.org/pdf/1805.01195.pdf)\n- LMNet: Real-time Multiclass Object Detection on CPU using 3D LiDAR [paper](https://arxiv.org/pdf/1805.04902.pdf)\n- HDNET: Exploit HD Maps for 3D Object Detection [paper](https://link.zhihu.com/?target=http%3A//proceedings.mlr.press/v87/yang18b/yang18b.pdf)\n- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation [paper](https://arxiv.org/pdf/1612.00593.pdf)\n- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space [paper](https://arxiv.org/abs/1706.02413)\n- IPOD: Intensive Point-based Object Detector for Point Cloud [paper](https://arxiv.org/abs/1812.05276v1)\n- PIXOR: Real-time 3D Object Detection from Point Clouds [paper](http://www.cs.toronto.edu/~wenjie/papers/cvpr18/pixor.pdf)\n- DepthCN: Vehicle Detection Using 3D-LIDAR and ConvNet [paper](https://www.baidu.com/link?url=EaE2zYjHkWvF33nsET2eNvbFGFu8-D3wWPia04uyKm95jMetHsSv3Zk-tODPGm5clsgCUgtVULsZ6IQqv0EYS_Z8El7Zzh57XzlJroSkaOuC8yv7r1XXL4bUrM2tWrTgjwqzfMV2tMTnFNbMOmHLTkUobgMg7HKoS6WW6PfQzkG\u0026wd=\u0026eqid=8f320cfa0005b878000000055e528b6d)\n- Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds [paper](https://arxiv.org/ftp/arxiv/papers/1907/1907.05286.pdf)\n- STD: Sparse-to-Dense 3D Object Detector for Point Cloud [paper](https://arxiv.org/abs/1907.10471)\n- Fast Point R-CNN [paper](https://arxiv.org/abs/1908.02990)\n- StarNet: Targeted Computation for Object Detection in Point Clouds [paper](https://arxiv.org/abs/1908.11069)\n- Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection [paper](https://arxiv.org/abs/1908.09492v1)\n- LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving [paper](https://arxiv.org/abs/1903.08701v1)\n- FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds[ paper](https://arxiv.org/abs/1903.10750v1)\n- Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud [paper](https://arxiv.org/abs/1907.03670v1)\n- PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud [paper](https://arxiv.org/abs/1812.04244)\n- Complex-YOLO: Real-time 3D Object Detection on Point Clouds [paper](https://arxiv.org/abs/1803.06199)\n- YOLO4D: A ST Approach for RT Multi-object Detection and Classification from LiDAR Point Clouds [paper](https://github.com/Tom-Hardy-3D-Vision-Workshop/awesome-3D-object-detection/blob/master)\n- YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud [paper](https://arxiv.org/abs/1808.02350)\n- Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud [paper](https://arxiv.org/pdf/1903.09847.pdf)\n- Pillar-based Object Detection for Autonomous Driving (ECCV2020) [paper](https://arxiv.org/abs/2007.10323)\n- EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection(ECCV2020) [paper](https://arxiv.org/abs/2007.08856)\n- Multi-Echo LiDAR for 3D Object Detection(ICCV2021) [paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Man_Multi-Echo_LiDAR_for_3D_Object_Detection_ICCV_2021_paper.pdf)\n- LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector(ICCV2021) [paper](https://arxiv.org/abs/2108.08258)\n- SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation(ICCV2021) [paper](https://arxiv.org/abs/2108.06709)\n- Structure Aware Single-stage 3D Object Detection from Point Cloud（CVPR2020) [paper](http://openaccess.thecvf.com/content_CVPR_2020/html/He_Structure_Aware_Single-Stage_3D_Object_Detection_From_Point_Cloud_CVPR_2020_paper.html) [code](https://github.com/skyhehe123/SA-SSD)\n- MLCVNet: Multi-Level Context VoteNet for 3D Object Detection（CVPR2020) [paper](https://arxiv.org/abs/2004.05679) [code](https://github.com/NUAAXQ/MLCVNet)\n- 3DSSD: Point-based 3D Single Stage Object Detector（CVPR2020） [paper](https://arxiv.org/abs/2002.10187) [code](https://github.com/tomztyang/3DSSD)\n- LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention（CVPR2020） [paper](https://arxiv.org/abs/2004.01389) [code](https://github.com/yinjunbo/3DVID)\n- PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection(CVPR2020) [paper](https://arxiv.org/abs/1912.13192) [code](https://github.com/sshaoshuai/PV-RCNN)\n- Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud（CVPR2020） [paper](https://arxiv.org/abs/2003.01251) [code](https://github.com/WeijingShi/Point-GNN)\n- MLCVNet: Multi-Level Context VoteNet for 3D Object Detection（CVPR2020） [paper](https://arxiv.org/pdf/2004.05679)\n- Density Based Clustering for 3D Object Detection in Point Clouds（CVPR2020） [paper](http://openaccess.thecvf.com/content_CVPR_2020/papers/Ahmed_Density-Based_Clustering_for_3D_Object_Detection_in_Point_Clouds_CVPR_2020_paper.pdf)\n- What You See is What You Get: Exploiting Visibility for 3D Object Detection（CVPR2020) [paper](https://arxiv.org/pdf/1912.04986.pdf)\n- PointPainting: Sequential Fusion for 3D Object Detection(CVPR2020) [paper](https://arxiv.org/pdf/1911.10150.pdf)\n- HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection（CVPR2020) [paper](https://arxiv.org/pdf/2003.00186)\n- LiDAR R-CNN: An Efficient and Universal 3D Object Detector（CVPR2021) [paper](https://arxiv.org/abs/2103.15297)\n- Center-based 3D Object Detection and Tracking(CVPR2021) [paper](https://arxiv.org/abs/2006.11275)\n- 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection(CVPR2021) [paper](https://arxiv.org/pdf/2012.04355.pdf)\n- Embracing Single Stride 3D Object Detector with Sparse Transformer(CVPR2022) [paper](https://arxiv.org/pdf/2112.06375.pdf), [code](https://github.com/TuSimple/SST)\n- Point Density-Aware Voxels for LiDAR 3D Object Detection(CVPR2022) [paper](https://arxiv.org/abs/2203.05662), [code](https://github.com/TRAILab/PDV)\n- A Unified Query-based Paradigm for Point Cloud Understanding(CVPR2022) [paper](https://arxiv.org/abs/2203.01252#:~:text=Abstract%3A%203D%20point%20cloud%20understanding,including%20detection%2C%20segmentation%20and%20classification.)\n- Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds(CVPR2022) [paper](https://arxiv.org/abs/2203.01252#:~:text=Abstract%3A%203D%20point%20cloud%20understanding,including%20detection%2C%20segmentation%20and%20classification.), [code](https://github.com/Ghostish/Open3DSOT)\n- Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds(CVPR2022) [paper](https://arxiv.org/abs/2203.11139), [code](https://github.com/yifanzhang713/IA-SSD)\n- Back To Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement(CVPR2022) [paper](http://arxiv.org/abs/2203.05238), [code](https://github.com/xuxw98/BackToReality)\n- Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds(CVPR2022) [paper](https://www4.comp.polyu.edu.hk/~cslzhang/paper/VoxSeT_cvpr22.pdf), [code](https://github.com/skyhehe123/VoxSeT)\n- BoxeR: Box-Attention for 2D and 3D Transformers(CVPR2022) [paper](https://arxiv.org/abs/2111.13087), [code](https://github.com/kienduynguyen/boxer), [中文介绍](https://mp.weixin.qq.com/s/UnUJJBwcAsRgz6TnQf_b7w)\n- Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes(CVPR2022) [paper](https://arxiv.org/abs/2011.12001), [code](https://github.com/qq456cvb/CanonicalVoting)\n- DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection(CVPR2022) [paper](https://arxiv.org/abs/2203.08195), [code](https://github.com/tensorflow/lingvo)\n- TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers. (CVPR2022) [paper](https://arxiv.org/abs/2203.11496), [code](https://github.com/xuyangbai/transfusion)\n- Point2Seq: Detecting 3D Objects as Sequences. (CVPR2022) [paper](https://arxiv.org/abs/2203.13394), [code](https://github.com/ocnflag/point2seq)\n- CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection(CVPR2022) [paper](https://arxiv.org/abs/2204.00325)\n- LiDAR Snowfall Simulation for Robust 3D Object Detection(CVPR2022) [paper](https://arxiv.org/abs/2203.15118), [code](https://github.com/syscv/lidar_snow_sim)\n- Unified Transformer Tracker for Object Tracking(CVPR2022) [paper](https://arxiv.org/abs/2203.15175), [code](https://github.com/visionml/pytracking)\n- Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion(CVPR2022) [paper](https://arxiv.org/abs/2203.09780)\n- M^2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation(CVPR2022) [paper](https://arxiv.org/abs/2204.05088)\n- RBGNet: Ray-based Grouping for 3D Object Detection(CVPR2022) [paper](https://arxiv.org/abs/2204.02251), [code](https://github.com/haiyang-w/rbgnet)\n- Fast Point Transformer(CVPR2022) [paper](https://arxiv.org/abs/2112.04702)\n- Focal Sparse Convolutional Networks for 3D Object Detection(CVPR2022) [paper](https://jiaya.me/papers/cvpr22_FocalSparseConv.pdf), [code](https://github.com/dvlab-research/FocalsConv)\n- FUTR3D: A Unified Sensor Fusion Framework for 3D Detection(CVPR2022) [paper](https://arxiv.org/abs/2203.10642)\n- VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention(CVPR2022) [paper](https://arxiv.org/abs/2203.09704), [code](https://github.com/Gorilla-Lab-SCUT/VISTA)\n- OccAM’s Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data(CVPR2022) [paper](https://link.zhihu.com/?target=https%3A//arxiv.org/pdf/2204.06577.pdf)\n- Voxel Field Fusion for 3D Object Detection(CVPR2022) [paper](https://arxiv.org/pdf/2205.15938.pdf), [code](https://github.com/dvlab-research/VFF)\n- FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels\n- LinK: Linear Kernel for LiDAR-based 3D Perception(CVPR2023) [paper](https://arxiv.org/abs/2303.16094), [code](https://github.com/MCG-NJU/LinK)\n- DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets(CVPR2023) [paper](https://arxiv.org/abs/2301.06051), [code](https://github.com/Haiyang-W/DSVT)\n- VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking(CVPR2023) [paper](https://arxiv.org/abs/2303.11301), [code](https://github.com/dvlab-research/VoxelNeXt)\n- LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs(CVPR2023) [paper](https://arxiv.org/abs/2206.10555),  [code](https://github.com/dvlab-research/LargeKernel3D)\n- FocalFormer3D : Focusing on Hard Instance for 3D Object Detection(ICCV2023) [paper](https://arxiv.org/abs/2308.04556), [code](https://github.com/NVlabs/FocalFormer3D)\n- CTRL: Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection(ICCV2023)  [paper](https://arxiv.org/abs/2304.12315), [code](https://github.com/tusen-ai/SST)\n- Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection(arxiv2023) [paper](https://arxiv.org/abs/2305.12853), [code](https://github.com/JinglinZhan/Real-Aug)\n## Competition Solution\n- [6th AI Driving Olympics, ICRA 2021](https://driving-olympics.ai/)\n- [5th AI Driving Olympics, NeurIPS 2020](https://driving-olympics.ai/)\n- [Workshop on Benchmarking Progress in Autonomous Driving, ICRA 2020](http://montrealrobotics.ca/driving-benchmarks/)\n- [Workshop on Autonomous Driving, CVPR 2019](https://sites.google.com/view/wad2019)\n## Engineering\n- Pointpillars-ONNX [code](https://github.com/SmallMunich/nutonomy_pointpillars)\n- Centerpoint-ONNX [code](https://github.com/CarkusL/CenterPoint)\n- BEVFormer-TensorRT [code](https://github.com/DerryHub/BEVFormer_tensorrt)\n## Survey\n- 2021.04 Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy [paper](https://www.sciencedirect.com/science/article/abs/pii/S1566253520304097)\n- 2021.07 3D Object Detection for Autonomous Driving: A Survey [paper](https://arxiv.org/abs/2106.10823)\n- 2021.07 Multi-Modal 3D Object Detection in Autonomous Driving: a Survey [paper](https://arxiv.org/abs/2106.12735)\n- 2021.10 A comprehensive survey of LIDAR-based 3D object detection methods with deep learning for autonomous driving [paper](https://www.sciencedirect.com/science/article/abs/pii/S0097849321001321)\n- 2021.12 Deep Learning for 3D Point Clouds: A Survey [paper](https://ieeexplore.ieee.org/abstract/document/9127813)\n## Book\n- 3D Object Detection Algorithms Based on Lidar and Camera: Design and Simulation [book](https://www.amazon.com/Object-Detection-Algorithms-Based-Camera/dp/6200536538)\n## Video\n- Aivia online workshop: 3D object detection and tracking [video](https://www.youtube.com/watch?v=P0TrkwAdFYQ)\n- 3D Object Retrieval 2021 workshop [video](https://3dor2021.github.io/programme.html)\n- 3D Deep Learning Tutorial from SU lab at UCSD [video](https://www.youtube.com/watch?v=vfL6uJYFrp4)\n- Lecture: Self-Driving Cars (Prof. Andreas Geiger, University of Tübingen) [video](https://www.youtube.com/watch?v=vfL6uJYFrp4)\n- Current Approaches and Future Directions for Point Cloud Object (2021.04) [video](https://www.youtube.com/watch?v=xFFCQVwYeec)\n- Latest 3D OBJECT DETECTION with 30+ FPS on CPU - MediaPipe and OpenCV Python (2021.05) [video](https://www.youtube.com/watch?v=f-Ibri14KMY)\n- MIT autonomous driving seminar (2019.11) [video](https://space.bilibili.com/174493426/channel/series)\n- sensetime seminar1 [video](https://www.bilibili.com/video/BV1Bf4y1b7PF?spm_id_from=333.999.0.0)\n- sensetime seminar2 [slides](https://docs.google.com/presentation/d/11CoKCxRFgzbIujMXxTZjHDo_hV0arEQ7sUFWFXWaX8o/edit#slide=id.p1)\n## Course\n- [University of Toronto, csc2541](http://www.cs.toronto.edu/~urtasun/courses/CSC2541/06_3D_detection.pdf)\n- [University of Tübingen, Self-Driving Cars](https://uni-tuebingen.de/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/autonomous-vision/lectures/self-driving-cars/) *(Strong Recommendation)*\n- [baidu-Udacity](https://apollo.auto/devcenter/devcenter.html)\n- [baidu-apollo](http://bit.baidu.com/Subject/index/id/16.html)\n- [University of Toronto, coursera](https://www.coursera.org/specializations/self-driving-cars?ranMID=40328\u0026ranEAID=9IqCvd3EEQc\u0026ranSiteID=9IqCvd3EEQc-MlZGCwEU2294XsVYWDNwzw\u0026siteID=9IqCvd3EEQc-MlZGCwEU2294XsVYWDNwzw\u0026utm_content=10\u0026utm_medium=partners\u0026utm_source=linkshare\u0026utm_campaign=9IqCvd3EEQc)\n\n## Blog\n- [Waymo Blog](https://blog.waymo.com/)\n- [apollo介绍之Perception模块](https://zhuanlan.zhihu.com/p/142401769)\n- [Apollo notes (Apollo学习笔记) - Apollo learning notes for beginners.](https://github.com/daohu527/Dig-into-Apollo#ledger-%E7%9B%AE%E5%BD%95)\n- [PointNet系列论文解读](https://zhuanlan.zhihu.com/p/44809266)\n- [Deep3dBox: 3D Bounding Box Estimation Using Deep Learning and Geometry](https://patrick-llgc.github.io/Learning-Deep-Learning/paper_notes/deep3dbox.html)\n- [SECOND算法解析](https://zhuanlan.zhihu.com/p/356892010)\n- [PointRCNN深度解读](https://zhuanlan.zhihu.com/p/361973979)\n- [Fast PointRCNN论文解读](https://zhuanlan.zhihu.com/p/363926237)\n- [PointPillars论文和代码解析](https://zhuanlan.zhihu.com/p/357626425)\n- [VoxelNet论文和代码解析](https://zhuanlan.zhihu.com/p/352419316)\n- [CenterPoint源码分析](https://zhuanlan.zhihu.com/p/444447881)\n- [PV-RCNN: 3D目标检测 Waymo挑战赛+KITTI榜 单模态第一算法](https://zhuanlan.zhihu.com/p/148942116)\n- [LiDAR R-CNN：一种快速、通用的二阶段3D检测器](https://zhuanlan.zhihu.com/p/359800738)\n- [混合体素网络（HVNet)](https://zhuanlan.zhihu.com/p/122426949)\n- [自动驾驶感知| Range Image paper分享](https://zhuanlan.zhihu.com/p/420708905)\n- [SST：单步长稀疏Transformer 3D物体检测器](https://zhuanlan.zhihu.com/p/476056546)\n## Famous Research Group/Scholar\n- [Naiyan Wang@Tusimple](https://scholar.google.com/citations?user=yAWtq6QAAAAJ\u0026hl=en)\n- [Hongsheng Li@CUHK](https://scholar.google.com/citations?user=BN2Ze-QAAAAJ\u0026hl=en)\n- [Oncel Tuzel@Apple](https://scholar.google.com/citations?user=Fe7NTe0AAAAJ\u0026hl=en)\n- [Oscar Beijbom@nuTonomy](https://scholar.google.com/citations?user=XP_Hxm4AAAAJ\u0026hl=en)\n- [Raquel Urtasun@University of Toronto](https://scholar.google.com/citations?user=jyxO2akAAAAJ\u0026hl=en)\n- [Philipp Krähenbühl@UT Austin](https://scholar.google.com/citations?hl=en\u0026user=dzOd2hgAAAAJ\u0026view_op=list_works\u0026sortby=pubdate)\n- [Deva Ramanan@CMU](https://scholar.google.com/citations?hl=en\u0026user=9B8PoXUAAAAJ\u0026view_op=list_works\u0026sortby=pubdate)\n- [Jiaya Jia@CUHK](https://jiaya.me/)\n- [Thomas Funkhouser@princeton](https://www.cs.princeton.edu/~funk/)\n- [Leonidas Guibas@Stanford](https://scholar.google.com/citations?hl=en\u0026user=5JlEyTAAAAAJ\u0026view_op=list_works\u0026sortby=pubdate)\n- [Steven Waslander@University of Toronto](https://www.trailab.utias.utoronto.ca/)\n- [Ouais Alsharif@Google Brain](https://scholar.google.com/citations?hl=en\u0026user=nFefEI8AAAAJ\u0026view_op=list_works\u0026sortby=pubdate)\n- [Yuning CHAI(former)@waymo](https://scholar.google.com/citations?hl=en\u0026user=i7U4YogAAAAJ\u0026view_op=list_works\u0026sortby=pubdate)\n- [Yulan Guo@NUDT](http://yulanguo.me/)\n- [Lei Zhang@The Hong Kong Polytechnic University](https://www4.comp.polyu.edu.hk/~cslzhang/)\n- [Hongyang Li@sensetime](https://lihongyang.info/)\n- [Luc Van Gool@ETH](https://scholar.google.com/citations?user=TwMib_QAAAAJ\u0026hl=en)\n- [Sanja Fidler@NVIDIA](https://scholar.google.com/citations?hl=en\u0026user=CUlqK5EAAAAJ\u0026view_op=list_works\u0026citft=1\u0026email_for_op=tianhaofu1%40gmail.com\u0026sortby=pubdate)\n- [Alan L. Yuille@JHU](https://www.cs.jhu.edu/~ayuille/)\n- [OpenDriveLab](https://github.com/OpenDriveLab)\n## Famous CodeBase\n- [Point Cloud Library (PCL)](https://github.com/PointCloudLibrary/pcl)\n- [Torchsparse](https://github.com/mit-han-lab/torchsparse)\n- [Spconv](https://github.com/traveller59/spconv)\n- [Det3D](https://github.com/poodarchu/Det3D)\n- [mmdetection3d](https://github.com/open-mmlab/mmdetection3d)\n- [OpenPCDet](https://github.com/open-mmlab/OpenPCDet)\n- [Centerpoint](https://github.com/tianweiy/CenterPoint)\n- [Apollo Auto - Baidu open autonomous driving platform](https://github.com/ApolloAuto)\n- [AutoWare - The University of Tokyo autonomous driving platform](https://www.autoware.org/)\n- [Openpilot - A open source software built to improve upon the existing driver assistance in most new cars on the road today](https://comma.ai/)\n- [DeepVision3D](https://github.com/dvlab-research/DeepVision3D)\n- [MinkowskiEngine](https://github.com/NVIDIA/MinkowskiEngine)\n\n\n## Famous Toolkit\n- [ZED Box](https://www.stereolabs.com/docs/object-detection/)\n\n# Acknowlegement\n[Awesome System for Machine Learning](https://github.com/HuaizhengZhang/Awesome-System-for-Machine-Learning)\n\n[awesome-3D-object-detection](https://github.com/Tom-Hardy-3D-Vision-Workshop/awesome-3D-object-detection)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTianhaoFu%2FAwesome-3D-Object-Detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTianhaoFu%2FAwesome-3D-Object-Detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTianhaoFu%2FAwesome-3D-Object-Detection/lists"}