mlsanityData to 7 Oct 2026

Offboard 3D Object Detection from Point Cloud Sequences

arXiv 2103.05073 ↗First posted 8 Mar 2021cs.CVcited by 144

Not on the map. Why?

Abstract (arXiv)

While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely under-explored, such as using machines to automatically generate high-quality 3D labels. Existing 3D object detectors fail to satisfy the high-quality requirement for offboard uses due to the limited input and speed constraints. In this paper, we propose a novel offboard 3D object detection pipeline using point cloud sequence data. Observing that different frames capture complementary views of objects, we design the offboard detector to make use of the temporal points through both multi-frame object detection and novel object-centric refinement models. Evaluated on the Waymo Open Dataset, our pipeline named 3D Auto Labeling shows significant gains compared to the state-of-the-art onboard detectors and our offboard baselines. Its performance is even on par with human labels verified through a human label study. Further experiments demonstrate the application of auto labels for semi-supervised learning and provide extensive analysis to validate various design choices.

Key facts. Cited by 144 papers in the map (data through 7 Oct 2026). Builds on 66 of its 82 references that are in the map. First posted on arXiv 8 Mar 2021.

Builds on

66 of 82 references.

References · 66

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  9. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  10. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  11. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  12. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
38 more
  1. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  2. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  3. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  4. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  5. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  6. 2019Confidence Regularized Self-Trainingcited by 418
  7. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  8. 2019What Makes Training Multi-Modal Classification Networks Hard?cited by 340
  9. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  10. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  11. 2019Label Propagation for Deep Semi-supervised Learningcited by 287
  12. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  13. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
  14. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 241
  15. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  16. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  17. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  18. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  19. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  20. 2019MVX-Net: Multimodal VoxelNet for 3D Object Detectioncited by 162
  21. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  22. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  23. 2018Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++cited by 119
  24. 2019Fast Point R-CNNcited by 119
  25. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  26. 2019MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequencescited by 117
  27. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111
  28. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 108
  29. 2016Vehicle Detection from 3D Lidar Using Fully Convolutional Networkcited by 105
  30. 2019Just Go with the Flow: Self-Supervised Scene Flow Estimationcited by 98
  31. 2019Fast Interactive Object Annotation with Curve-GCNcited by 95
  32. 2017Annotating Object Instances with a Polygon-RNNcited by 88
  33. 2020HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detectioncited by 82
  34. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  35. 2019Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priorscited by 74
  36. 2016Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networkscited by 72
  37. 2019What You See is What You Get: Exploiting Visibility for 3D Object Detectioncited by 69
  38. 2020Weakly Supervised 3D Object Detection from Lidar Point Cloudcited by 67

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 37; 2023: 38; 2024: 33; 2025: 15; 2026: 7.

144 papers.

Sort:

By area:

  1. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  2. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  3. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  4. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  5. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  6. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 485
  7. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 238
  8. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  9. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 191
  10. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  11. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  12. 2024Towards learning-based planning:The nuPlan benchmark for real-world autonomous drivingcited by 103
38 more
  1. 2021SimpleTrack: Understanding and Rethinking 3D Multi-object Trackingcited by 102
  2. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  3. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  4. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  5. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  6. 2022Differentiable Raycasting for Self-supervised Occupancy Forecastingcited by 83
  7. 2022Multi-modal Sensor Fusion for Auto Driving Perception: A Surveycited by 73
  8. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 72
  9. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  10. 2022MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detectioncited by 65
  11. 2023Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perceptioncited by 65
  12. 2022Motion Inspired Unsupervised Perception and Prediction in Autonomous Drivingcited by 59
  13. 2021ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 57
  14. 2022Waymo Open Dataset: Panoramic Video Panoptic Segmentationcited by 57
  15. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Modelcited by 57
  16. 2022Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 55
  17. 2023PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Cloudscited by 54
  18. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
  19. 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
  20. 2023TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUscited by 36
  21. 2024ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformerscited by 36
  22. 2022PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detectioncited by 33
  23. 2023Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encodingcited by 32
  24. 2023BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregationcited by 31
  25. 2023DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Cloudscited by 31
  26. 2023Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detectioncited by 28
  27. 2024Segment Anything Model for Road Network Graph Extractioncited by 28
  28. 2024AIDE: An Automatic Data Engine for Object Detection in Autonomous Drivingcited by 26
  29. 2022No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfacescited by 25
  30. 2021From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detectioncited by 24
  31. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  32. 2023LEOD: Label-Efficient Object Detection for Event Camerascited by 24
  33. 2022HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Drivingcited by 22
  34. 2021Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detectioncited by 21
  35. 2022MotionCNN: A Strong Baseline for Motion Prediction in Autonomous Drivingcited by 21
  36. 2022DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detectioncited by 20
  37. 2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19
  38. 2023MV-Map: Offboard HD-Map Generation with Multi-view Consistencycited by 19

50 most cited of 144 All 144 (JSON)