mlsanityData to 14 Oct 2026

CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusion

arXiv 2212.01247 ↗First posted 2 Dec 2022cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

To track the 3D locations and trajectories of the other traffic participants at any given time, modern autonomous vehicles are equipped with multiple cameras that cover the vehicle's full surroundings. Yet, camera-based 3D object tracking methods prioritize optimizing the single-camera setup and resort to post-hoc fusion in a multi-camera setup. In this paper, we propose a method for panoramic 3D object tracking, called CC-3DT, that associates and models object trajectories both temporally and across views, and improves the overall tracking consistency. In particular, our method fuses 3D detections from multiple cameras before association, reducing identity switches significantly and improving motion modeling. Our experiments on large-scale driving datasets show that fusion before association leads to a large margin of improvement over post-hoc fusion. We set a new state-of-the-art with 12.6% improvement in average multi-object tracking accuracy (AMOTA) among all camera-based methods on the competitive NuScenes 3D tracking benchmark, outperforming previously published methods by 6.5% in AMOTA with the same 3D detector.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 53 of its 67 references that are in the map. First posted on arXiv 2 Dec 2022.

Builds on

53 of 67 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  9. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  10. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  11. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  12. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
38 more
  1. 2019Objects as Pointscited by 1,175
  2. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  3. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  4. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 910
  5. 2016Simple Online and Realtime Trackingcited by 868
  6. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  7. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 518
  8. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  9. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 490
  10. 2020Tracking Objects as Pointscited by 483
  11. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
  12. 2019Tracking without bells and whistlescited by 382
  13. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 381
  14. 2020TransTrack: Multiple Object Tracking with Transformercited by 371
  15. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  16. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 278
  17. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 252
  18. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
  19. 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
  20. 2019Disentangling Monocular 3D Object Detectioncited by 217
  21. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  22. 2017Detect to Track and Track to Detectcited by 131
  23. 2019CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identificationcited by 119
  24. 2021SimpleTrack: Understanding and Rethinking 3D Multi-object Trackingcited by 103
  25. 2022MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queriescited by 91
  26. 2016Learning to Track at 100 FPS with Deep Regression Networkscited by 89
  27. 2018Features for Multi-Target Multi-Camera Tracking and Re-Identificationcited by 88
  28. 2021EagerMOT: 3D Multi-Object Tracking via Sensor Fusioncited by 83
  29. 2021Monocular Quasi-Dense 3D Object Trackingcited by 81
  30. 2016Learning by tracking: Siamese CNN for robust target associationcited by 79
  31. 2018Joint Monocular 3D Vehicle Detection and Trackingcited by 77
  32. 2016POI: Multiple Object Tracking with High Performance Detection and Appearance Featurecited by 74
  33. 2020RetinaTrack: Online Single Stage Joint Detection and Trackingcited by 67
  34. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  35. 2021DEFT: Detection Embeddings for Trackingcited by 56
  36. 2021Exploring Simple 3D Multi-Object Tracking for Autonomous Drivingcited by 56
  37. 2019Track to Reconstruct and Reconstruct to Trackcited by 49
  38. 2018Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Trackingcited by 40

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 13; 2024: 9; 2025: 4; 2026: 5.

31 papers.

Sort:

By area:

  1. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  2. 2023CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perceptioncited by 82
  3. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 75
  4. 2023Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perceptioncited by 65
  5. 2023Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Trackingcited by 54
  6. 2024SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Drivingcited by 47
  7. 2024SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Controlcited by 32
  8. 2023RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloudcited by 21
  9. 2023Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detectioncited by 14
  10. 2023F2BEV: Bird's Eye View Generation from Surround-View Fisheye Camera Images for Automated Drivingcited by 12
  11. 2023S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representationscited by 12
  12. 2023DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Trackingcited by 11
19 more
  1. 2023Delving into Motion-Aware Matching for Monocular 3D Object Trackingcited by 11
  2. 2024Fast-Poly: A Fast Polyhedral Framework For 3D Multi-Object Trackingcited by 11
  3. 2025GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splattingcited by 11
  4. 20253D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detectioncited by 11
  5. 2024CR3DT: Camera-RADAR Fusion for 3D Detection and Trackingcited by 10
  6. 2024RCTrans: Radar-Camera Transformer via Radar Densifier and Sequential Decoder for 3D Object Detectioncited by 7
  7. 2023Weakly Supervised 3D Object Detection with Multi-Stage Generalizationcited by 2
  8. 2024S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Trackingcited by 2
  9. 2024Cyclic Refiner: Object-Aware Temporal Representation Learning for Multi-View 3D Detection and Trackingcited by 2
  10. 2024RockTrack: A 3D Robust Multi-Camera-Ken Multi-Object Tracking Frameworkcited by 2
  11. 2024SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Trackingcited by 2
  12. 2026ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Trackingcited by 2
  13. 2025Bayesian Approximation-Based Trajectory Prediction and Tracking with 4D Radarcited by 1
  14. 2025LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detectioncited by 1
  15. 2026Radar-Informed 3D Multi-Object Tracking under Adverse Conditionscited by 1
  16. 2026Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputscited by 1
  17. 2023Visual Perception System for Autonomous Drivingcited by 0
  18. 2026GraphBEV++: Multi-Modal Feature Alignment for Autonomous Drivingcited by 0
  19. 2026DVPSFormer: Efficient Online Depth-aware Video Panoptic Segmentation for Autonomous Drivingcited by 0