mlsanityData to 7 Oct 2026

PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds

arXiv 2108.06455 ↗First posted 14 Aug 2021cs.CVcited by 59

Not on the map. Why?

Abstract (arXiv)

3D single object tracking is a key issue for robotics. In this paper, we propose a transformer module called Point-Track-Transformer (PTT) for point cloud-based 3D single object tracking. PTT module contains three blocks for feature embedding, position encoding, and self-attention feature computation. Feature embedding aims to place features closer in the embedding space if they have similar semantic information. Position encoding is used to encode coordinates of point clouds into high dimension distinguishable features. Self-attention generates refined attention features by computing attention weights. Besides, we embed the PTT module into the open-source state-of-the-art method P2B to construct PTT-Net. Experiments on the KITTI dataset reveal that our PTT-Net surpasses the state-of-the-art by a noticeable margin (~10%). Additionally, PTT-Net could achieve real-time performance (~40FPS) on NVIDIA 1080Ti GPU. Our code is open-sourced for the robotics community at https://github.com/shanjiayao/PTT.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 19 of its 26 references that are in the map. First posted on arXiv 14 Aug 2021.

Builds on

19 of 26 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2020Point Transformercited by 1,462
  5. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  6. 2020PCT: Point cloud transformercited by 730
  7. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  8. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  9. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  10. 2020Exploring Self-attention for Image Recognitioncited by 313
  11. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  12. 2019Local Relation Networks for Image Recognitioncited by 210
7 more
  1. 2015A Novel Performance Evaluation Methodology for Single-Target Trackerscited by 113
  2. 2020P2B: Point-to-Box Network for 3D Object Tracking in Point Cloudscited by 84
  3. 2019Leveraging Shape Completion for 3D Siamese Trackingcited by 74
  4. 20213D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloudcited by 45
  5. 2019Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Cloudscited by 35
  6. 2018Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filterscited by 32
  7. 2020F-Siamese Tracker: A Frustum-based Double Siamese Network for 3D Single Object Trackingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 13; 2023: 19; 2024: 15; 2025: 8; 2026: 3.

59 papers.

Sort:

By area:

  1. 2021PTTR: Relational 3D Point Cloud Object Tracking with Transformercited by 65
  2. 2022Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 55
  3. 20223D Siamese Transformer Network for Single Object Tracking on Point Cloudscited by 44
  4. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  5. 2022CXTrack: Improving 3D Point Cloud Tracking with Contextual Informationcited by 28
  6. 2022Real-time 3D Single Object Tracking with Transformercited by 27
  7. 2023MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priorscited by 24
  8. 2022A Lightweight and Detector-free 3D Single Object Tracker on Point Cloudscited by 23
  9. 2022GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Cloudscited by 23
  10. 2025SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overheadcited by 23
  11. 2022Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformercited by 18
  12. 2025MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusioncited by 18
38 more
  1. 2023OSP2B: One-Stage Point-to-Box Network for 3D Siamese Trackingcited by 16
  2. 2023Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Trackingcited by 16
  3. 2022Exploiting More Information in Sparse Point Cloud for 3D Single Object Trackingcited by 14
  4. 2023An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 14
  5. 2024Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encodercited by 14
  6. 2024Towards Category Unification of 3D Single Object Tracking on Point Cloudscited by 13
  7. 2023Correlation Pyramid Network for 3D Single Object Trackingcited by 10
  8. 2023STTracker: Spatio-Temporal Tracker for 3D Single Object Trackingcited by 10
  9. 2023M3SOT: Multi-frame, Multi-field, Multi-space 3D Single Object Trackingcited by 10
  10. 2024P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Cloudscited by 10
  11. 2024MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cuescited by 10
  12. 2025CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Trackingcited by 9
  13. 2023Modeling Continuous Motion for 3D Point Cloud Object Trackingcited by 8
  14. 2023Robust 3D Tracking with Quality-Aware Shape Completioncited by 7
  15. 2022Implicit and Efficient Point Cloud Completion for 3D Single Object Trackingcited by 6
  16. 2024SeqTrack3D: Exploring Sequence Information for Robust 3D Point Cloud Trackingcited by 6
  17. 2022Towards Class-agnostic Tracking Using Feature Decorrelation in Point Cloudscited by 5
  18. 2022OST: Efficient One-stream Network for 3D Single Object Tracking in Point Cloudscited by 5
  19. 2023GLT-T++: Global-Local Transformer for 3D Siamese Tracking with Ranking Losscited by 4
  20. 2024Sub-SA: Strengthen In-context Learning via Submodular Selective Annotationcited by 4
  21. 20243D Single-object Tracking in Point Clouds with High Temporal Variationcited by 4
  22. 2025TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Trackingcited by 4
  23. 2025Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Trackingcited by 4
  24. 2022VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Imagescited by 3
  25. 2023MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistencycited by 3
  26. 2023Multi-View Representation is What You Need for Point-Cloud Pre-Trainingcited by 3
  27. 2023Motion-to-Matching: A Mixed Paradigm for 3D Single Object Trackingcited by 3
  28. 2024FlowTrack: Point-level Flow Network for 3D Single Object Trackingcited by 3
  29. 2022Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Trackingcited by 2
  30. 2023Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Mapscited by 2
  31. 2023BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye Viewcited by 2
  32. 2024PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Cloudscited by 2
  33. 2024Rethinking Attention Module Design for Point Cloud Analysiscited by 2
  34. 2024GSOT3D: Towards Generic 3D Single Object Tracking in the Wildcited by 2
  35. 2026TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Trackingcited by 2
  36. 2023MMF-Track: Multi-modal Multi-level Fusion for 3D Single Object Trackingcited by 1
  37. 2023Multi-Correlation Siamese Transformer Network with Dense Connection for 3D Single Object Trackingcited by 1
  38. 2024Small Object Tracking in LiDAR Point Cloud: Learning the Target-awareness Prototype and Fine-grained Search Regioncited by 1

50 most cited of 59 All 59 (JSON)