mlsanityData to 14 Oct 2026

Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds

arXiv 2203.11139 ↗First posted 21 Mar 2022cs.CV cs.ROcited by 131

Not on the map. Why?

Abstract (arXiv)

We study the problem of efficient object detection of 3D LiDAR point clouds. To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic random sampling or farthest point sampling to progressively downsample input point clouds, despite the fact that not all points are equally important to the task of object detection. In particular, the foreground points are inherently more important than background points for object detectors. Motivated by this, we propose a highly-efficient single-stage point-based 3D detector in this paper, termed IA-SSD. The key of our approach is to exploit two learnable, task-oriented, instance-aware downsampling strategies to hierarchically select the foreground points belonging to objects of interest. Additionally, we also introduce a contextual centroid perception module to further estimate precise instance centers. Finally, we build our IA-SSD following the encoder-only architecture for efficiency. Extensive experiments conducted on several large-scale detection benchmarks demonstrate the competitive performance of our IA-SSD. Thanks to the low memory footprint and a high degree of parallelism, it achieves a superior speed of 80+ frames-per-second on the KITTI dataset with a single RTX2080Ti GPU. The code is available at urlhttps://github.com/yifanzhang713/IA-SSD.

Key facts. Cited by 131 papers in the map (data through 14 Oct 2026). Builds on 51 of its 60 references that are in the map. First posted on arXiv 21 Mar 2022.

Builds on

51 of 60 references.

References · 51

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  9. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  10. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  11. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  12. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
38 more
  1. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  2. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  3. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  4. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 368
  5. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  6. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  7. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  8. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  9. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 326
  10. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  11. 2021Voxel Transformer for 3D Object Detectioncited by 247
  12. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  13. 2017Submanifold Sparse Convolutional Networkscited by 223
  14. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  15. 2017Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Ratescited by 199
  16. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  17. 2020SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registrationcited by 142
  18. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  19. 2019IoU Loss for 2D/3D Object Detectioncited by 128
  20. 2019Fast Point R-CNNcited by 119
  21. 2019TANet: Robust 3D Object Detection from Point Clouds with Triple Attentioncited by 108
  22. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  23. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  24. 2019SESS: Self-Ensembling Semi-Supervised 3D Object Detectioncited by 89
  25. 2020HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detectioncited by 82
  26. 2020End-to-End Pseudo-LiDAR for Image-Based 3D Object Detectioncited by 80
  27. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  28. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  29. 2018Complex-YOLO: Real-time 3D Object Detection on Point Cloudscited by 57
  30. 2021Learning Semantic Segmentation of Large-Scale Point Clouds with Random Samplingcited by 51
  31. 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 50
  32. 2021HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detectioncited by 47
  33. 2019Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Cloudscited by 35
  34. 2018YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloudcited by 32
  35. 2020Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detectioncited by 31
  36. 2021Spatial-Temporal Transformer for 3D Point Cloud Sequencescited by 22
  37. 2020SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloudcited by 16
  38. 20203D IoU-Net: IoU Guided 3D Object Detector for Point Cloudscited by 15

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 18; 2023: 55; 2024: 31; 2025: 22; 2026: 5.

131 papers.

Sort:

By area:

  1. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 222
  2. 2023Generalized Relation Modeling for Transformer Trackingcited by 93
  3. 2022Fully Sparse 3D Object Detectioncited by 84
  4. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  5. 2022Transformation-Equivariant 3D Object Detection for Autonomous Drivingcited by 52
  6. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 47
  7. 2023Uni3D: A Unified Baseline for Multi-dataset 3D Object Detectioncited by 39
  8. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  9. 2022SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloudcited by 37
  10. 2023FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxelscited by 34
  11. 2023Super Sparse 3D Object Detectioncited by 32
  12. 2023OcTr: Octree-based Transformer for 3D Object Detectioncited by 32
38 more
  1. 2022Towards Efficient 3D Object Detection with Knowledge Distillationcited by 29
  2. 2023Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labelingcited by 28
  3. 2022CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detectioncited by 27
  4. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  5. 2022DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detectioncited by 25
  6. 2023Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detectioncited by 24
  7. 2022A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attackscited by 22
  8. 2023PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videoscited by 22
  9. 2024LISO: Lidar-only Self-Supervised 3D Object Detectioncited by 22
  10. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  11. 2024SEED: A Simple and Effective 3D DETR in Point Cloudscited by 19
  12. 2023DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detectioncited by 18
  13. 2023CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementaritycited by 18
  14. 2025Perspective-Invariant 3D Object Detectioncited by 18
  15. 2023Human-centric Scene Understanding for 3D Large-scale Scenarioscited by 17
  16. 2023Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videoscited by 16
  17. 2023MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequencescited by 15
  18. 2023Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAMcited by 15
  19. 2022itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detectioncited by 14
  20. 2023MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detectioncited by 14
  21. 2023SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detectioncited by 14
  22. 2023Curricular Object Manipulation in LiDAR-based Object Detectioncited by 12
  23. 2023Robust 3D Object Detection from LiDAR-Radar Point Clouds via Cross-Modal Feature Augmentationcited by 12
  24. 2024UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gapscited by 12
  25. 20243D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidancecited by 12
  26. 20253EED: Ground Everything Everywhere in 3Dcited by 12
  27. 20223D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detectioncited by 11
  28. 2023Unleash the Potential of Image Branch for Cross-modal 3D Object Detectioncited by 11
  29. 2023T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learningcited by 11
  30. 2024ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attentioncited by 11
  31. 2024Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detectioncited by 11
  32. 2024DUFOMap: Efficient Dynamic Awareness Mappingcited by 11
  33. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 11
  34. 2024V2X-PC: Vehicle-to-everything Collaborative Perception via Point Clustercited by 10
  35. 2025UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detectioncited by 10
  36. 2025FSHNet: Fully Sparse Hybrid Network for 3D Object Detectioncited by 9
  37. 2023A Dynamic Points Removal Benchmark in Point Cloud Mapscited by 8
  38. 2023GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Cloudscited by 8

50 most cited of 131 All 131 (JSON)