mlsanityData to 7 Oct 2026

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

arXiv 1912.13192 ↗First posted 31 Dec 2019cs.CV cs.LG eess.IVcited by 890

Not on the map. Why?

Abstract (arXiv)

We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our proposed method deeply integrates both 3D voxel Convolutional Neural Network (CNN) and PointNet-based set abstraction to learn more discriminative point cloud features. It takes advantages of efficient learning and high-quality proposals of the 3D voxel CNN and the flexible receptive fields of the PointNet-based networks. Specifically, the proposed framework summarizes the 3D scene with a 3D voxel CNN into a small set of keypoints via a novel voxel set abstraction module to save follow-up computations and also to encode representative scene features. Given the high-quality 3D proposals generated by the voxel CNN, the RoI-grid pooling is proposed to abstract proposal-specific features from the keypoints to the RoI-grid points via keypoint set abstraction with multiple receptive fields. Compared with conventional pooling operations, the RoI-grid feature points encode much richer context information for accurately estimating object confidences and locations. Extensive experiments on both the KITTI dataset and the Waymo Open dataset show that our proposed PV-RCNN surpasses state-of-the-art 3D detection methods with remarkable margins by using only point clouds. Code is available at https://github.com/open-mmlab/OpenPCDet.

Key facts. Cited by 890 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 137; 2022: 212; 2023: 214; 2024: 171; 2025: 109; 2026: 47.

890 papers.

Sort:

By area:

  1. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  2. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  3. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  4. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  5. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 442
  6. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  7. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  8. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  9. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  10. 2021OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communicationcited by 304
  11. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
  12. 2021Voxel Transformer for 3D Object Detectioncited by 247
38 more
  1. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  2. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  3. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  4. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  5. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  6. 2021Group-Free 3D Object Detection via Transformerscited by 215
  7. 2023Scene as Occupancycited by 208
  8. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 199
  9. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  10. 2023Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Followingcited by 192
  11. 2021PandaSet: Advanced Sensor Suite Dataset for Autonomous Drivingcited by 186
  12. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  13. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  14. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 168
  15. 2021Multimodal Virtual Point 3D Detectioncited by 166
  16. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
  17. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  18. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 155
  19. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 144
  20. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  21. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  22. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  23. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  24. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  25. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
  26. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  27. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  28. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  29. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  30. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  31. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  32. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  33. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  34. 2023Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Drivingcited by 112
  35. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  36. 2022MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformercited by 108
  37. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  38. 20213D Object Detection for Autonomous Driving: A Surveycited by 106

50 most cited of 890 All 890 (JSON)