mlsanityData to 13 Oct 2026

PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection

arXiv 2102.00463 ↗First posted 31 Jan 2021cs.CVcited by 232

Not on the map. Why?

Abstract (arXiv)

3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object detection on point clouds. First, we propose a novel 3D detector, PV-RCNN, which boosts the 3D detection performance by deeply integrating the feature learning of both point-based set abstraction and voxel-based sparse convolution through two novel steps, i.e., the voxel-to-keypoint scene encoding and the keypoint-to-grid RoI feature abstraction. Second, we propose an advanced framework, PV-RCNN++, for more efficient and accurate 3D object detection. It consists of two major improvements: sectorized proposal-centric sampling for efficiently producing more representative keypoints, and VectorPool aggregation for better aggregating local point features with much less resource consumption. With these two strategies, our PV-RCNN++ is about 3× faster than PV-RCNN, while also achieving better performance. The experiments demonstrate that our proposed PV-RCNN++ framework achieves state-of-the-art 3D detection performance on the large-scale and highly-competitive Waymo Open Dataset with 10 FPS inference speed on the detection range of 150m * 150m.

Key facts. Cited by 232 papers in the map (data through 13 Oct 2026). Builds on 85 of its 122 references that are in the map. First posted on arXiv 31 Jan 2021.

Builds on

85 of 122 references.

References · 85

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,625
  2. 2020End-to-End Object Detection with Transformerscited by 7,396
  3. 2017Mask R-CNNcited by 7,266
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,231
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,027
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,840
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,389
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,128
  9. 2015Fast R-CNNcited by 2,933
  10. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,440
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,222
  12. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,709
38 more
  1. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,575
  2. 2016YOLO9000: Better, Faster, Strongercited by 1,430
  3. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  4. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,205
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,203
  7. 2019Objects as Pointscited by 1,173
  8. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  9. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  11. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  12. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  13. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  14. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 747
  15. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 722
  16. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  17. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  18. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  19. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  20. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  21. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  22. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  23. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  24. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  25. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  26. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 367
  27. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  28. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  29. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  30. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  31. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  32. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  33. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 277
  34. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  35. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
  36. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  37. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  38. 2017Submanifold Sparse Convolutional Networkscited by 223

50 most cited of 85 All 85 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 15; 2022: 40; 2023: 61; 2024: 64; 2025: 36; 2026: 16.

232 papers.

Sort:

By area:

  1. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 847
  2. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  3. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  4. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 193
  5. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 159
  6. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  7. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  8. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
  9. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  10. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  11. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  12. 2021Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weathercited by 95
38 more
  1. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  2. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  3. 2022Latency-Aware Collaborative Perceptioncited by 86
  4. 2022Fully Sparse 3D Object Detectioncited by 84
  5. 2023Collaboration Helps Camera Overtake LiDAR in 3D Detectioncited by 81
  6. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  7. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  8. 2023UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representationcited by 74
  9. 2022TorchSparse: Efficient Point Cloud Inference Enginecited by 73
  10. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  11. 2022LiDAR Snowfall Simulation for Robust 3D Object Detectioncited by 72
  12. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 72
  13. 2022Point Density-Aware Voxels for LiDAR 3D Object Detectioncited by 70
  14. 2024Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detectioncited by 66
  15. 2022MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detectioncited by 65
  16. 2022Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoderscited by 58
  17. 2023FocalFormer3D : Focusing on Hard Instance for 3D Object Detectioncited by 58
  18. 2021ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 57
  19. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  20. 2023PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Cloudscited by 54
  21. 2022Transformation-Equivariant 3D Object Detection for Autonomous Drivingcited by 52
  22. 2024SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detectioncited by 52
  23. 2022NeRF-RPN: A general framework for object detection in NeRFscited by 46
  24. 2023HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Cloudscited by 45
  25. 2022RBGNet: Ray-based Grouping for 3D Object Detectioncited by 40
  26. 2023SAM3D: Zero-Shot 3D Object Detection via Segment Anything Modelcited by 40
  27. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 40
  28. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  29. 2023Uni3D: A Unified Baseline for Multi-dataset 3D Object Detectioncited by 39
  30. 2024MonoCD: Monocular 3D Object Detection with Complementary Depthscited by 38
  31. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  32. 2023FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxelscited by 34
  33. 2023MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representationscited by 33
  34. 2024GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detectioncited by 33
  35. 2023Super Sparse 3D Object Detectioncited by 32
  36. 2023OcTr: Octree-based Transformer for 3D Object Detectioncited by 32
  37. 2022Towards Efficient 3D Object Detection with Knowledge Distillationcited by 29
  38. 2022Adaptive Feature Fusion for Cooperative Perception using LiDAR Point Cloudscited by 29

50 most cited of 232 All 232 (JSON)