mlsanityData to 7 Oct 2026

PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Clouds

arXiv 2404.07495 ↗First posted 11 Apr 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

LiDAR-based 3D single object tracking (3D SOT) is a critical issue in robotics and autonomous driving. Existing 3D SOT methods typically adhere to a point-based processing pipeline, wherein the re-sampling operation invariably leads to either redundant or missing information, thereby impacting performance. To address these issues, we propose PillarTrack, a novel pillar-based 3D SOT framework. First, we transform sparse point clouds into dense pillars to preserve the local and global geometrics. Second, we propose a Pyramid-Encoded Pillar Feature Encoder (PE-PFE) design to enhance the robustness of pillar feature for translation/rotation/scale. Third, we present an efficient Transformer-based backbone from the perspective of modality differences. Finally, we construct our PillarTrack based on above designs. Extensive experiments show that our method achieves comparable performance on the KITTI and NuScenes datasets, significantly enhancing the performance of the baseline.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 41 of its 67 references that are in the map. First posted on arXiv 11 Apr 2024.

Builds on

41 of 67 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  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. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  10. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  11. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  12. 2020Point Transformercited by 1,462
29 more
  1. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  2. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  3. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  4. 2018How Does Batch Normalization Help Optimization?cited by 355
  5. 2015A Novel Performance Evaluation Methodology for Single-Target Trackerscited by 113
  6. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  7. 2020P2B: Point-to-Box Network for 3D Object Tracking in Point Cloudscited by 84
  8. 2019Leveraging Shape Completion for 3D Siamese Trackingcited by 74
  9. 2021Box-Aware Feature Enhancement for Single Object Tracking on Point Cloudscited by 66
  10. 2021PTTR: Relational 3D Point Cloud Object Tracking with Transformercited by 65
  11. 2021PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Cloudscited by 59
  12. 2022Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Imagescited by 56
  13. 2022Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 55
  14. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  15. 20213D Object Tracking with Transformercited by 49
  16. 20213D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloudcited by 45
  17. 20223D Siamese Transformer Network for Single Object Tracking on Point Cloudscited by 44
  18. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  19. 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detectioncited by 29
  20. 2022Real-time 3D Single Object Tracking with Transformercited by 27
  21. 2022GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Cloudscited by 23
  22. 2022Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformercited by 18
  23. 2022Exploiting More Information in Sparse Point Cloud for 3D Single Object Trackingcited by 14
  24. 2023An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 14
  25. 2024Towards Category Unification of 3D Single Object Tracking on Point Cloudscited by 13
  26. 2022OST: Efficient One-stream Network for 3D Single Object Tracking in Point Cloudscited by 5
  27. 2023SCA-PVNet: Self-and-Cross Attention Based Aggregation of Point Cloud and Multi-View for 3D Object Retrievalcited by 3
  28. 2023SelFLoc: Selective Feature Fusion for Large-scale Point Cloud-based Place Recognitioncited by 2
  29. 2024Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object Detectioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

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

2 papers.

  1. 2025CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Trackingcited by 9
  2. 2026MAETrack: Unleashing the Potential of Pretrained Geometric Priors for 3D Single Object Trackingcited by 0