mlsanityData to 7 Oct 2026

MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues

arXiv 2412.02734 ↗First posted 3 Dec 2024cs.CV cs.ROcited by 10

Not on the map. Why?

Abstract (arXiv)

3D single object tracking is essential in autonomous driving and robotics. Existing methods often struggle with sparse and incomplete point cloud scenarios. To address these limitations, we propose a Multimodal-guided Virtual Cues Projection (MVCP) scheme that generates virtual cues to enrich sparse point clouds. Additionally, we introduce an enhanced tracker MVCTrack based on the generated virtual cues. Specifically, the MVCP scheme seamlessly integrates RGB sensors into LiDAR-based systems, leveraging a set of 2D detections to create dense 3D virtual cues that significantly improve the sparsity of point clouds. These virtual cues can naturally integrate with existing LiDAR-based 3D trackers, yielding substantial performance gains. Extensive experiments demonstrate that our method achieves competitive performance on the NuScenes dataset.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 36 of its 44 references that are in the map. First posted on arXiv 3 Dec 2024.

Builds on

36 of 44 references.

References · 36

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2019Objects as Pointscited by 1,172
  3. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  4. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  5. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  6. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  7. 2021Multimodal Virtual Point 3D Detectioncited by 166
  8. 2015A Novel Performance Evaluation Methodology for Single-Target Trackerscited by 113
  9. 2020P2B: Point-to-Box Network for 3D Object Tracking in Point Cloudscited by 84
  10. 2021EagerMOT: 3D Multi-Object Tracking via Sensor Fusioncited by 83
  11. 2019Leveraging Shape Completion for 3D Siamese Trackingcited by 74
  12. 2021Box-Aware Feature Enhancement for Single Object Tracking on Point Cloudscited by 66
24 more
  1. 2021PTTR: Relational 3D Point Cloud Object Tracking with Transformercited by 65
  2. 2021PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Cloudscited by 59
  3. 2022Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 55
  4. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  5. 20213D Object Tracking with Transformercited by 49
  6. 20213D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloudcited by 45
  7. 20223D Siamese Transformer Network for Single Object Tracking on Point Cloudscited by 44
  8. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  9. 2022Real-time 3D Single Object Tracking with Transformercited by 27
  10. 2023MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priorscited by 24
  11. 2022A Lightweight and Detector-free 3D Single Object Tracker on Point Cloudscited by 23
  12. 2022GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Cloudscited by 23
  13. 2022Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformercited by 18
  14. 2023OSP2B: One-Stage Point-to-Box Network for 3D Siamese Trackingcited by 16
  15. 2023Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Trackingcited by 16
  16. 2022Exploiting More Information in Sparse Point Cloud for 3D Single Object Trackingcited by 14
  17. 2023An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 14
  18. 2024Towards Category Unification of 3D Single Object Tracking on Point Cloudscited by 13
  19. 2020F-Siamese Tracker: A Frustum-based Double Siamese Network for 3D Single Object Trackingcited by 11
  20. 2023STTracker: Spatio-Temporal Tracker for 3D Single Object Trackingcited by 10
  21. 2024P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Cloudscited by 10
  22. 2022Learning Localization-aware Target Confidence for Siamese Visual Trackingcited by 7
  23. 2024FlowTrack: Point-level Flow Network for 3D Single Object Trackingcited by 3
  24. 2023MMF-Track: Multi-modal Multi-level Fusion for 3D Single Object Trackingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 4.

10 papers.

  1. 2025MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusioncited by 18
  2. 2025CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Trackingcited by 9
  3. 2026FocusTrack: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Trackingcited by 7
  4. 2025Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Trackingcited by 4
  5. 2025TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognitioncited by 4
  6. 2026TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Trackingcited by 2
  7. 2025FADE: Adversarial Concept Erasure in Flow Modelscited by 0
  8. 2025Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustnesscited by 0
  9. 2026SAVTrack: Selective Vote Aggregation for Reliability-Aware Point Cloud Trackingcited by 0
  10. 2026MAETrack: Unleashing the Potential of Pretrained Geometric Priors for 3D Single Object Trackingcited by 0