/awesome-3D-object-detection

3D object detection

作者：Tom Hardy

公众号：3D视觉工坊

公众号运营者和嘉宾介绍：运营者来自国内一线大厂的算法工程师，深研3D视觉、vSLAM、计算机视觉、点云处理、深度学习、自动驾驶、图像处理、三维重建等领域，特邀嘉宾包括国内外知名高校的博士硕士，旷视、商汤、百度、阿里等就职的算法大佬，欢迎一起交流学习！

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~

一、基于点云的三维目标检测算法

  1. End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds
  2. Vehicle Detection from 3D Lidar Using Fully Convolutional Network(百度早期工作)
  3. VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
  4. Object Detection and Classification in Occupancy Grid Maps using Deep Convolutional Networks
  5. RT3D: Real-Time 3-D Vehicle Detection in LiDAR Point Cloud for Autonomous Driving
  6. BirdNet: a 3D Object Detection Framework from LiDAR information
  7. LMNet: Real-time Multiclass Object Detection on CPU using 3D LiDAR
  8. HDNET: Exploit HD Maps for 3D Object Detection
  9. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
  10. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
  11. IPOD: Intensive Point-based Object Detector for Point Cloud
  12. PIXOR: Real-time 3D Object Detection from Point Clouds
  13. DepthCN: Vehicle Detection Using 3D-LIDAR and ConvNet
  14. Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds
  15. STD: Sparse-to-Dense 3D Object Detector for Point Cloud
  16. Fast Point R-CNN
  17. StarNet: Targeted Computation for Object Detection in Point Clouds
  18. Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
  19. LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
  20. FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds
  21. Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud
  22. PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
  23. Complex-YOLO: Real-time 3D Object Detection on Point Clouds
  24. YOLO4D: A ST Approach for RT Multi-object Detection and Classification from LiDAR Point Clouds
  25. YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud
  26. Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud
  27. Structure Aware Single-stage 3D Object Detection from Point Cloud（CVPR2020) 源代码
  28. MLCVNet: Multi-Level Context VoteNet for 3D Object Detection（CVPR2020) 源代码
  29. 3DSSD: Point-based 3D Single Stage Object Detector（CVPR2020） 源代码
  30. LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention（CVPR2020） 源代码
  31. PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection(CVPR2020) 源代码
  32. Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud（CVPR2020） 源代码
  33. MLCVNet: Multi-Level Context VoteNet for 3D Object Detection（CVPR2020）
  34. Density Based Clustering for 3D Object Detection in Point Clouds（CVPR2020）
  35. What You See is What You Get: Exploiting Visibility for 3D Object Detection（CVPR2020)
  36. PointPainting: Sequential Fusion for 3D Object Detection(CVPR2020)
  37. HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection（CVPR2020)
  38. LiDAR R-CNN: An Efficient and Universal 3D Object Detector（CVPR2021)
  39. Center-based 3D Object Detection and Tracking(CVPR2021)
  40. 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection(CVPR2021)

二、基于单目的三维目标检测算法

  1. Task-Aware Monocular Depth Estimation for 3D Object Detection
  2. M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
  3. Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
  4. Disentangling Monocular 3D Object Detection
  5. Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints
  6. Monocular 3D Object Detection via Geometric Reasoning on Keypoints
  7. Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction
  8. GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
  9. Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
  10. Task-Aware Monocular Depth Estimation for 3D Object Detection
  11. M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
  12. Deconvolutional Networks for Point-Cloud Vehicle Detection and Tracking in Driving Scenarios
  13. Learning Depth-Guided Convolutions for Monocular 3D Object Detection（CVPR2020）
  14. End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection（CVPR2020）
  15. GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection(CVPR2021)
  16. Delving into Localization Errors for Monocular 3D Object Detection(CVPR2021)
  17. M3DSSD: Monocular 3D Single Stage Object Detector(CVPR2021)
  18. MonoRUn: Monocular 3D Object Detection by Self-Supervised Reconstruction and Uncertainty Propagation(CVPR2021)
  19. Categorical Depth Distribution Network for Monocular 3D Object Detection(CVPR2021)

三、基于双目的三维目标检测算法

  1. Object-Centric Stereo Matching for 3D Object Detection
  2. Triangulation Learning Network: from Monocular to Stereo 3D Object Detection
  3. Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
  4. Stereo R-CNN based 3D Object Detection for Autonomous Driving
  5. IDA-3D: Instance-Depth-Aware 3D Object Detection from Stereo Vision for Autonomous Driving（CVPR2020） 源代码
  6. Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation（CVPR2020) 源代码
  7. DSGN: Deep Stereo Geometry Network for 3D Object Detection(CVPR2020) 源代码

四、基于RGB-D的三维目标检测算法

  1. Frustum PointNets for 3D Object Detection from RGB-D Data
  2. Frustum VoxNet for 3D object detection from RGB-D or Depth images

五、基于Radar和RGB方式的三维目标检测算法

  1. CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection

六、基于融合数据的三维目标检测算法

  1. MLOD: A multi-view 3D object detection based on robust feature fusion method
  2. Multi-Sensor 3D Object Box Refinement for Autonomous Driving
  3. Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
  4. Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation
  5. Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images
  6. MVX-Net: Multimodal VoxelNet for 3D Object Detection
  7. Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation
  8. 3D Object Detection Using Scale Invariant and Feature Reweighting Networks
  9. End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection（CVPR2020） 源代码