├── images ├── image-20200223231758890.png ├── image-20200223231827080.png ├── image-20200223231856518.png ├── image-20200223231920757.png └── README.md /images: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /image-20200223231758890.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hardy-Uint/awesome-3D-object-detection/HEAD/image-20200223231758890.png -------------------------------------------------------------------------------- /image-20200223231827080.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hardy-Uint/awesome-3D-object-detection/HEAD/image-20200223231827080.png -------------------------------------------------------------------------------- /image-20200223231856518.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hardy-Uint/awesome-3D-object-detection/HEAD/image-20200223231856518.png -------------------------------------------------------------------------------- /image-20200223231920757.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hardy-Uint/awesome-3D-object-detection/HEAD/image-20200223231920757.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 2 | 主要针对3D object相关算法进行了汇总，分为基于RGB图像、RGB-D数据、立体视觉、点云、融合等方式，欢迎补充~ 3 | 4 | ### 一、基于点云的三维目标检测算法 5 | 6 | 1. [End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds](https://github.com/Tom-Hardy-3D-Vision-Workshop/awesome-3D-object-detection/blob/master) 7 | 2. [Vehicle Detection from 3D Lidar Using Fully Convolutional Network(百度早期工作)](https://arxiv.org/abs/1608.07916) 8 | 3. [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://arxiv.org/pdf/1711.06396.pdf) 9 | 4. [Object Detection and Classification in Occupancy Grid Maps using Deep Convolutional Networks](https://arxiv.org/pdf/1805.08689.pdf) 10 | 5. [RT3D: Real-Time 3-D Vehicle Detection in LiDAR Point Cloud for Autonomous Driving](https://www.onacademic.com/detail/journal_1000040467923610_4dfe.html) 11 | 6. [BirdNet: a 3D Object Detection Framework from LiDAR information](https://arxiv.org/pdf/1805.01195.pdf) 12 | 7. [LMNet: Real-time Multiclass Object Detection on CPU using 3D LiDAR](https://arxiv.org/pdf/1805.04902.pdf) 13 | 8. [HDNET: Exploit HD Maps for 3D Object Detection](https://link.zhihu.com/?target=http%3A//proceedings.mlr.press/v87/yang18b/yang18b.pdf) 14 | 9. [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://arxiv.org/pdf/1612.00593.pdf) 15 | 10. [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://arxiv.org/abs/1706.02413) 16 | 11. [IPOD: Intensive Point-based Object Detector for Point Cloud](https://arxiv.org/abs/1812.05276v1) 17 | 12. [PIXOR: Real-time 3D Object Detection from Point Clouds](http://www.cs.toronto.edu/~wenjie/papers/cvpr18/pixor.pdf) 18 | 13. [DepthCN: Vehicle Detection Using 3D-LIDAR and ConvNet](https://www.baidu.com/link?url=EaE2zYjHkWvF33nsET2eNvbFGFu8-D3wWPia04uyKm95jMetHsSv3Zk-tODPGm5clsgCUgtVULsZ6IQqv0EYS_Z8El7Zzh57XzlJroSkaOuC8yv7r1XXL4bUrM2tWrTgjwqzfMV2tMTnFNbMOmHLTkUobgMg7HKoS6WW6PfQzkG&wd=&eqid=8f320cfa0005b878000000055e528b6d) 19 | 14. [Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds](https://arxiv.org/ftp/arxiv/papers/1907/1907.05286.pdf) 20 | 15. [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://arxiv.org/abs/1907.10471) 21 | 16. [Fast Point R-CNN](https://arxiv.org/abs/1908.02990) 22 | 17. [StarNet: Targeted Computation for Object Detection in Point Clouds](https://arxiv.org/abs/1908.11069) 23 | 18. [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://arxiv.org/abs/1908.09492v1) 24 | 19. [LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving](https://arxiv.org/abs/1903.08701v1) 25 | 20. [FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds](https://arxiv.org/abs/1903.10750v1) 26 | 21. [Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud](https://arxiv.org/abs/1907.03670v1) 27 | 22. [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://arxiv.org/abs/1812.04244) 28 | 23. [Complex-YOLO: Real-time 3D Object Detection on Point Clouds](https://arxiv.org/abs/1803.06199) 29 | 24. [YOLO4D: A ST Approach for RT Multi-object Detection and Classification from LiDAR Point Clouds](https://github.com/Tom-Hardy-3D-Vision-Workshop/awesome-3D-object-detection/blob/master) 30 | 25. [YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud](https://arxiv.org/abs/1808.02350) 31 | 26. [Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud](https://arxiv.org/pdf/1903.09847.pdf) 32 | 27. [Structure Aware Single-stage 3D Object Detection from Point Cloud（CVPR2020)](http://openaccess.thecvf.com/content_CVPR_2020/html/He_Structure_Aware_Single-Stage_3D_Object_Detection_From_Point_Cloud_CVPR_2020_paper.html) [源代码](https://github.com/skyhehe123/SA-SSD) 33 | 28. [MLCVNet: Multi-Level Context VoteNet for 3D Object Detection（CVPR2020)](https://arxiv.org/abs/2004.05679) [源代码](https://github.com/NUAAXQ/MLCVNet) 34 | 29. [3DSSD: Point-based 3D Single Stage Object Detector（CVPR2020）](https://arxiv.org/abs/2002.10187) [源代码](https://github.com/tomztyang/3DSSD) 35 | 30. [LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention（CVPR2020）](https://arxiv.org/abs/2004.01389) [源代码](https://github.com/yinjunbo/3DVID) 36 | 31. [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection(CVPR2020)](https://arxiv.org/abs/1912.13192) [源代码](https://github.com/sshaoshuai/PV-RCNN) 37 | 32. [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud（CVPR2020）](https://arxiv.org/abs/2003.01251) [源代码](https://github.com/WeijingShi/Point-GNN) 38 | 33. [MLCVNet: Multi-Level Context VoteNet for 3D Object Detection（CVPR2020）](https://arxiv.org/pdf/2004.05679) 39 | 34. [Density Based Clustering for 3D Object Detection in Point Clouds（CVPR2020）](http://openaccess.thecvf.com/content_CVPR_2020/papers/Ahmed_Density-Based_Clustering_for_3D_Object_Detection_in_Point_Clouds_CVPR_2020_paper.pdf) 40 | 35. [What You See is What You Get: Exploiting Visibility for 3D Object Detection（CVPR2020)](https://arxiv.org/pdf/1912.04986.pdf) 41 | 36. [PointPainting: Sequential Fusion for 3D Object Detection(CVPR2020)](https://arxiv.org/pdf/1911.10150.pdf) 42 | 37. [HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection（CVPR2020)](https://arxiv.org/pdf/2003.00186) 43 | 38. [LiDAR R-CNN: An Efficient and Universal 3D Object Detector（CVPR2021)](https://arxiv.org/abs/2103.15297) 44 | 39. [Center-based 3D Object Detection and Tracking(CVPR2021)](https://arxiv.org/abs/2006.11275) 45 | 40. [3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection(CVPR2021)](https://arxiv.org/pdf/2012.04355.pdf) 46 | 47 | ### 二、基于单目的三维目标检测算法 48 | 49 | 1. [Task-Aware Monocular Depth Estimation for 3D Object Detection](https://arxiv.org/abs/1909.07701) 50 | 2. [M3D-RPN: Monocular 3D Region Proposal Network for Object Detection](https://arxiv.org/abs/1907.06038v1) 51 | 3. [Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss](https://arxiv.org/pdf/1906.08070.pdf) 52 | 4. [Disentangling Monocular 3D Object Detection](https://arxiv.org/pdf/1905.12365v1.pdf) 53 | 5. [Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints](https://arxiv.org/pdf/1905.09970.pdf) 54 | 6. [Monocular 3D Object Detection via Geometric Reasoning on Keypoints](https://arxiv.org/abs/1905.05618?context=cs.CV) 55 | 7. [Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction](https://arxiv.org/abs/1904.01690) 56 | 8. [GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving](https://arxiv.org/abs/1903.10955) 57 | 9. [Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving](https://arxiv.org/abs/1903.11444?context=cs.CV) 58 | 10. [Task-Aware Monocular Depth Estimation for 3D Object Detection](https://arxiv.org/abs/1909.07701) 59 | 11. [M3D-RPN: Monocular 3D Region Proposal Network for Object Detection](https://arxiv.org/abs/1907.06038v1) 60 | 12. [Deconvolutional Networks for Point-Cloud Vehicle Detection and Tracking in Driving Scenarios](https://arxiv.org/abs/1808.07935) 61 | 13. [Learning Depth-Guided Convolutions for Monocular 3D Object Detection（CVPR2020）](http://openaccess.thecvf.com/content_CVPR_2020/papers/Ding_Learning_Depth-Guided_Convolutions_for_Monocular_3D_Object_Detection_CVPR_2020_paper.pdf) 62 | 14. [End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection（CVPR2020）](http://openaccess.thecvf.com/content_CVPR_2020/papers/Qian_End-to-End_Pseudo-LiDAR_for_Image-Based_3D_Object_Detection_CVPR_2020_paper.pdf) 63 | 15. [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection(CVPR2021)](https://arxiv.org/abs/2103.17202) 64 | 16. [Delving into Localization Errors for Monocular 3D Object Detection(CVPR2021)](https://arxiv.org/abs/2103.16237) 65 | 17. [M3DSSD: Monocular 3D Single Stage Object Detector(CVPR2021)](https://arxiv.org/abs/2103.13164) 66 | 18. [MonoRUn: Monocular 3D Object Detection by Self-Supervised Reconstruction and Uncertainty Propagation(CVPR2021)](https://arxiv.org/abs/2103.12605) 67 | 19. [Categorical Depth Distribution Network for Monocular 3D Object Detection(CVPR2021)](https://arxiv.org/abs/2103.01100) 68 | 69 | ### 三、基于双目的三维目标检测算法 70 | 71 | 1. [Object-Centric Stereo Matching for 3D Object Detection](https://arxiv.org/pdf/1909.07566.pdf) 72 | 2. [Triangulation Learning Network: from Monocular to Stereo 3D Object Detection](https://arxiv.org/pdf/1906.01193.pdf) 73 | 3. [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](http://www.cs.cornell.edu/~yanwang/project/plidar/) 74 | 4. [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://arxiv.org/pdf/1902.09738.pdf) 75 | 5. [IDA-3D: Instance-Depth-Aware 3D Object Detection from Stereo Vision for Autonomous Driving（CVPR2020）](http://openaccess.thecvf.com/content_CVPR_2020/papers/Peng_IDA-3D_Instance-Depth-Aware_3D_Object_Detection_From_Stereo_Vision_for_Autonomous_CVPR_2020_paper.pdf) [源代码](https://github.com/swords123/IDA-3D) 76 | 6. [Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation（CVPR2020)](https://arxiv.org/abs/2004.03572) [源代码](https://github.com/zju3dv/disprcn) 77 | 7. [DSGN: Deep Stereo Geometry Network for 3D Object Detection(CVPR2020)](https://arxiv.org/abs/2001.03398) [源代码](https://github.com/chenyilun95/DSGN) 78 | 79 | ### 四、基于RGB-D的三维目标检测算法 80 | 81 | 1. Frustum PointNets for 3D Object Detection from RGB-D Data 82 | 2. Frustum VoxNet for 3D object detection from RGB-D or Depth images 83 | 84 | ### 五、基于Radar和RGB方式的三维目标检测算法 85 | 86 | 1. [CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection](https://link.zhihu.com/?target=https%3A//arxiv.org/pdf/2011.04841.pdf) 87 | 88 | 89 | 90 | ### 六、基于融合数据的三维目标检测算法 91 | 92 | 1. [MLOD: A multi-view 3D object detection based on robust feature fusion method](https://arxiv.org/abs/1909.04163v1) 93 | 2. [Multi-Sensor 3D Object Box Refinement for Autonomous Driving](https://arxiv.org/abs/1909.04942?context=cs) 94 | 3. [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://arxiv.org/abs/1906.06310v1) 95 | 4. [Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation](https://arxiv.org/abs/1907.06777) 96 | 5. [Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images](https://arxiv.org/abs/1907.09081) 97 | 6. [MVX-Net: Multimodal VoxelNet for 3D Object Detection](https://arxiv.org/pdf/1904.01649.pdf) 98 | 7. [Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation](https://arxiv.org/abs/1904.11466v1) 99 | 8. [3D Object Detection Using Scale Invariant and Feature Reweighting Networks](https://arxiv.org/abs/1901.02237v1) 100 | 9. [End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection（CVPR2020）](https://arxiv.org/abs/2004.03080) [源代码](https://github.com/mileyan/pseudo-LiDAR_e2e) 101 | --------------------------------------------------------------------------------