mlsanityData to 7 Oct 2026

PointPillars: Fast Encoders for Object Detection from Point Clouds

arXiv 1812.05784 ↗First posted 14 Dec 2018cs.LG cs.CV stat.MLcited by 1,707

Not on the map. Why?

Cited by 86 in End-to-end autonomous driving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline. Recent literature suggests two types of encoders; fixed encoders tend to be fast but sacrifice accuracy, while encoders that are learned from data are more accurate, but slower. In this work we propose PointPillars, a novel encoder which utilizes PointNets to learn a representation of point clouds organized in vertical columns (pillars). While the encoded features can be used with any standard 2D convolutional detection architecture, we further propose a lean downstream network. Extensive experimentation shows that PointPillars outperforms previous encoders with respect to both speed and accuracy by a large margin. Despite only using lidar, our full detection pipeline significantly outperforms the state of the art, even among fusion methods, with respect to both the 3D and bird's eye view KITTI benchmarks. This detection performance is achieved while running at 62 Hz: a 2 - 4 fold runtime improvement. A faster version of our method matches the state of the art at 105 Hz. These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.

Key facts. Cited by 1,707 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 184; 2022: 328; 2023: 407; 2024: 324; 2025: 288; 2026: 175.

1,707 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. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  4. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  5. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  6. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  7. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 485
  8. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 482
  9. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 477
  10. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  11. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  12. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
38 more
  1. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  2. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  3. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  4. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  5. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  6. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  7. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  8. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  9. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 311
  10. 2021OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communicationcited by 304
  11. 2023LMDrive: Closed-Loop End-to-End Driving with Large Language Modelscited by 301
  12. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 288
  13. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  14. 2021HDMapNet: An Online HD Map Construction and Evaluation Frameworkcited by 280
  15. 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 270
  16. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  17. 2022Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Mapscited by 255
  18. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  19. 2021Voxel Transformer for 3D Object Detectioncited by 247
  20. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 243
  21. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  22. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  23. 2024EMMA: End-to-End Multimodal Model for Autonomous Drivingcited by 226
  24. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  25. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  26. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  27. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  28. 2021MP3: A Unified Model to Map, Perceive, Predict and Plancited by 211
  29. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  30. 2022FUTR3D: A Unified Sensor Fusion Framework for 3D Detectioncited by 194
  31. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  32. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  33. 2022BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Drivingcited by 191
  34. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  35. 2021PandaSet: Advanced Sensor Suite Dataset for Autonomous Drivingcited by 186
  36. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  37. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
  38. 2021Multimodal Virtual Point 3D Detectioncited by 166

50 most cited of 1,707 All 1,707 (JSON)