mlsanityData to 7 Oct 2026

Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection

arXiv 2304.02867 ↗First posted 6 Apr 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Efficient representation of point clouds is fundamental for LiDAR-based 3D object detection. While recent grid-based detectors often encode point clouds into either voxels or pillars, the distinctions between these approaches remain underexplored. In this paper, we quantify the differences between the current encoding paradigms and highlight the limited vertical learning within. To tackle these limitations, we introduce a hybrid Voxel-Pillar Fusion network (VPF), which synergistically combines the unique strengths of both voxels and pillars. Specifically, we first develop a sparse voxel-pillar encoder that encodes point clouds into voxel and pillar features through 3D and 2D sparse convolutions respectively, and then introduce the Sparse Fusion Layer (SFL), facilitating bidirectional interaction between sparse voxel and pillar features. Our efficient, fully sparse method can be seamlessly integrated into both dense and sparse detectors. Leveraging this powerful yet straightforward framework, VPF delivers competitive performance, achieving real-time inference speeds on the nuScenes and Waymo Open Dataset. The code will be available.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 43 of its 54 references that are in the map. First posted on arXiv 6 Apr 2023.

Builds on

43 of 54 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  8. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  9. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  10. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  11. 2018SlowFast Networks for Video Recognitioncited by 1,862
  12. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
31 more
  1. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  2. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  3. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  4. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  5. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  6. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  7. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  8. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  9. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  10. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  11. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  12. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  13. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  14. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  15. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  16. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  17. 2019Scale-Aware Trident Networks for Object Detectioncited by 159
  18. 2020CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detectioncited by 147
  19. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  20. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  21. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  22. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  23. 2017Dual Path Networkscited by 119
  24. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  25. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  26. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  27. 2022Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Cloudscited by 102
  28. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  29. 2019Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspotscited by 84
  30. 2022VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attentioncited by 48
  31. 2023LinK: Linear Kernel for LiDAR-based 3D Perceptioncited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Voxel Densification for Serialized 3D Object Detection: Mitigating Sparsity via Pre-serialization Expansioncited by 0
  2. 2025PointSlice: Accurate and Efficient Slice-Based Representation for 3D Object Detection from Point Cloudscited by 0
  3. 2026PIRATR: Parametric Object Inference for Robotic Applications with Transformers in 3D Point Cloudscited by 0