mlsanityData to 14 Oct 2026

From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network

arXiv 1907.03670 ↗First posted 8 Jul 2019cs.CVcited by 368

Not on the map. Why?

Abstract (arXiv)

3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications. In this paper, we extend our preliminary work PointRCNN to a novel and strong point-cloud-based 3D object detection framework, the part-aware and aggregation neural network (Part-A2 net). The whole framework consists of the part-aware stage and the part-aggregation stage. Firstly, the part-aware stage for the first time fully utilizes free-of-charge part supervisions derived from 3D ground-truth boxes to simultaneously predict high quality 3D proposals and accurate intra-object part locations. The predicted intra-object part locations within the same proposal are grouped by our new-designed RoI-aware point cloud pooling module, which results in an effective representation to encode the geometry-specific features of each 3D proposal. Then the part-aggregation stage learns to re-score the box and refine the box location by exploring the spatial relationship of the pooled intra-object part locations. Extensive experiments are conducted to demonstrate the performance improvements from each component of our proposed framework. Our Part-A2 net outperforms all existing 3D detection methods and achieves new state-of-the-art on KITTI 3D object detection dataset by utilizing only the LiDAR point cloud data. Code is available at https://github.com/sshaoshuai/PointCloudDet3D.

Key facts. Cited by 368 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 75; 2022: 91; 2023: 82; 2024: 63; 2025: 45; 2026: 12.

368 papers.

Sort:

By area:

  1. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  2. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 466
  3. 2021Voxel Transformer for 3D Object Detectioncited by 247
  4. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  5. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 222
  6. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  7. 2021Learning Distilled Collaboration Graph for Multi-Agent Perceptioncited by 194
  8. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  9. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 167
  10. 2021Multimodal Virtual Point 3D Detectioncited by 166
  11. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 159
  12. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
38 more
  1. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  2. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  3. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  4. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  5. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 129
  6. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  7. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  8. 2021CKConv: Continuous Kernel Convolution For Sequential Datacited by 120
  9. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  10. 2023Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Drivingcited by 114
  11. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  12. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  13. 2024UniScene: Unified Occupancy-centric Driving Scene Generationcited by 106
  14. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  15. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  16. 2021Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weathercited by 97
  17. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 94
  18. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  19. 2022Fully Sparse 3D Object Detectioncited by 84
  20. 2021MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagationcited by 82
  21. 2022Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completioncited by 82
  22. 2024RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detectioncited by 82
  23. 2023Virtual Sparse Convolution for Multimodal 3D Object Detectioncited by 81
  24. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  25. 20213D Semantic Scene Completion: a Surveycited by 74
  26. 2021M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformerscited by 74
  27. 2023UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representationcited by 74
  28. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  29. 2022LiDAR Snowfall Simulation for Robust 3D Object Detectioncited by 73
  30. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 73
  31. 2022LargeKernel3D: Scaling up Kernels in 3D Sparse CNNscited by 72
  32. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 70
  33. 2022AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detectioncited by 70
  34. 2022Point Density-Aware Voxels for LiDAR 3D Object Detectioncited by 70
  35. 2023MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Drivingcited by 68
  36. 2021Back-tracing Representative Points for Voting-based 3D Object Detection in Point Cloudscited by 67
  37. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 67
  38. 2021Box-Aware Feature Enhancement for Single Object Tracking on Point Cloudscited by 66

50 most cited of 368 All 368 (JSON)