mlsanityData to 7 Oct 2026

3D Single-object Tracking in Point Clouds with High Temporal Variation

arXiv 2408.02049 ↗First posted 4 Aug 2024cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of the point clouds and the motion of the objects across neighboring frames are smooth, failing to cope with high temporal variation data. In this paper, we present a novel framework for 3D SOT in point clouds with high temporal variation, called HVTrack. HVTrack proposes three novel components to tackle the challenges in the high temporal variation scenario: 1) A Relative-Pose-Aware Memory module to handle temporal point cloud shape variations; 2) a Base-Expansion Feature Cross-Attention module to deal with similar object distractions in expanded search areas; 3) a Contextual Point Guided Self-Attention module for suppressing heavy background noise. We construct a dataset with high temporal variation (KITTI-HV) by setting different frame intervals for sampling in the KITTI dataset. On the KITTI-HV with 5 frame intervals, our HVTrack surpasses the state-of-the-art tracker CXTracker by 11.3%/15.7% in Success/Precision.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 38 of its 51 references that are in the map. First posted on arXiv 4 Aug 2024.

Builds on

38 of 51 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  5. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  8. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  9. 2020Tracking Objects as Pointscited by 483
  10. 2020GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learningcited by 113
  11. 2020P2B: Point-to-Box Network for 3D Object Tracking in Point Cloudscited by 84
  12. 20233D Registration with Maximal Cliquescited by 83
26 more
  1. 2019Leveraging Shape Completion for 3D Siamese Trackingcited by 74
  2. 2021Box-Aware Feature Enhancement for Single Object Tracking on Point Cloudscited by 66
  3. 2021PTTR: Relational 3D Point Cloud Object Tracking with Transformercited by 65
  4. 2020Probabilistic 3D Multi-Object Tracking for Autonomous Drivingcited by 64
  5. 2021PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Cloudscited by 59
  6. 2021Exploring Simple 3D Multi-Object Tracking for Autonomous Drivingcited by 56
  7. 2022Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 55
  8. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  9. 20213D Object Tracking with Transformercited by 49
  10. 20213D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloudcited by 45
  11. 20223D Siamese Transformer Network for Single Object Tracking on Point Cloudscited by 44
  12. 2021Immortal Tracker: Tracklet Never Diescited by 42
  13. 2018Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filterscited by 32
  14. 2023SG-Former: Self-guided Transformer with Evolving Token Reallocationcited by 32
  15. 2022CXTrack: Improving 3D Point Cloud Tracking with Contextual Informationcited by 28
  16. 2022Real-time 3D Single Object Tracking with Transformercited by 27
  17. 2021Model-free Vehicle Tracking and State Estimation in Point Cloud Sequencescited by 25
  18. 2023MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priorscited by 24
  19. 2022ShaSTA: Modeling Shape and Spatio-Temporal Affinities for 3D Multi-Object Trackingcited by 21
  20. 20233DMOTFormer: Graph Transformer for Online 3D Multi-Object Trackingcited by 21
  21. 2019Efficient Bird Eye View Proposals for 3D Siamese Trackingcited by 18
  22. 2023TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypothesescited by 14
  23. 2023M3SOT: Multi-frame, Multi-field, Multi-space 3D Single Object Trackingcited by 10
  24. 2021SDOF-Tracker: Fast and Accurate Multiple Human Tracking by Skipped-Detection and Optical-Flowcited by 7
  25. 2023Hierarchical Prior Mining for Non-local Multi-View Stereocited by 7
  26. 2023MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistencycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024GSOT3D: Towards Generic 3D Single Object Tracking in the Wildcited by 2
  2. 2026GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editingcited by 1
  3. 2025MambaTrack3D: A State Space Model Framework for LiDAR-Based Object Tracking under High Temporal Variationcited by 0
  4. 2026Temporally Consistent Long-Term Memory for 3D Single Object Trackingcited by 0