mlsanityData to 7 Oct 2026

Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving

arXiv 2109.11615 ↗First posted 23 Sep 2021cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

Sharing collective perception messages (CPM) between vehicles is investigated to decrease occlusions so as to improve the perception accuracy and safety of autonomous driving. However, highly accurate data sharing and low communication overhead is a big challenge for collective perception, especially when real-time communication is required among connected and automated vehicles. In this paper, we propose an efficient and effective keypoints-based deep feature fusion framework built on the 3D object detector PV-RCNN, called Fusion PV-RCNN (FPV-RCNN for short), for collective perception. We introduce a high-performance bounding box proposal matching module and a keypoints selection strategy to compress the CPM size and solve the multi-vehicle data fusion problem. Besides, we also propose an effective localization error correction module based on the maximum consensus principle to increase the robustness of the data fusion. Compared to a bird's-eye view (BEV) keypoints feature fusion, FPV-RCNN achieves improved detection accuracy by about 9% at a high evaluation criterion (IoU 0.7) on the synthetic dataset COMAP dedicated to collective perception. In addition, its performance is comparable to two raw data fusion baselines that have no data loss in sharing. Moreover, our method also significantly decreases the CPM size to less than 0.3 KB, and is thus about 50 times smaller than the BEV feature map sharing used in previous works. Even with further decreased CPM feature channels, i.e., from 128 to 32, the detection performance does not show apparent drops. The code of our method is available at https://github.com/YuanYunshuang/FPV_RCNN.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 16 of its 31 references that are in the map. First posted on arXiv 23 Sep 2021.

Builds on

16 of 31 references.

References · 16

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  6. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  7. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  8. 2020V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Predictioncited by 292
  9. 2017Submanifold Sparse Convolutional Networkscited by 223
  10. 2019F-Cooper: Feature based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Cloudscited by 171
  11. 2019Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Cloudscited by 165
  12. 2020LiDARsim: Realistic LiDAR Simulation by Leveraging the Real Worldcited by 137
4 more
  1. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  2. 2015Sparse 3D convolutional neural networkscited by 71
  3. 2020Demonstrations of Cooperative Perception: Safety and Robustness in Connected and Automated Vehicle Operationscited by 11
  4. 2020Feature Sharing and Integration for Cooperative Cognition and Perception with Volumetric Sensorscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 13; 2024: 8; 2025: 10; 2026: 4.

45 papers.

Sort:

By area:

  1. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  2. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  3. 2022V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Drivingcited by 157
  4. 2022Robust Collaborative 3D Object Detection in Presence of Pose Errorscited by 129
  5. 2023Collaborative Perception in Autonomous Driving: Methods, Datasets and Challengescited by 87
  6. 2022Latency-Aware Collaborative Perceptioncited by 86
  7. 2022Bridging the Domain Gap for Multi-Agent Perceptioncited by 60
  8. 2023CORE: Cooperative Reconstruction for Multi-Agent Perceptioncited by 41
  9. 2023Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perceptioncited by 38
  10. 2024RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perceptioncited by 37
  11. 2022V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perceptioncited by 28
  12. 2023Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Drivingcited by 25
33 more
  1. 2023Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?cited by 22
  2. 2022A Survey and Framework of Cooperative Perception: From Heterogeneous Singleton to Hierarchical Cooperationcited by 21
  3. 2023BM2CP: Efficient Collaborative Perception with LiDAR-Camera Modalitiescited by 20
  4. 2023DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perceptioncited by 17
  5. 2023Vehicle-to-Everything Cooperative Perception for Autonomous Drivingcited by 15
  6. 2025SparseAlign: A Fully Sparse Framework for Cooperative Object Detectioncited by 15
  7. 2022A Cooperative Perception System Robust to Localization Errorscited by 14
  8. 2024A Survey on Intermediate Fusion Methods for Collaborative Perception Categorized by Real World Challengescited by 13
  9. 2023On Data Fabrication in Collaborative Vehicular Perception: Attacks and Countermeasurescited by 11
  10. 2022Collaborative Perception for Autonomous Driving: Current Status and Future Trendcited by 10
  11. 2023Generating Evidential BEV Maps in Continuous Driving Spacecited by 10
  12. 2025Collaborative Perception Datasets for Autonomous Driving: A Reviewcited by 8
  13. 2023Collective PV-RCNN: A Novel Fusion Technique using Collective Detections for Enhanced Local LiDAR-Based Perceptioncited by 6
  14. 2025Systematic Literature Review on Vehicular Collaborative Perception -- A Computer Vision Perspectivecited by 5
  15. 2025Which2comm: An Efficient Collaborative Perception Framework for 3D Object Detectioncited by 4
  16. 2025V2X-DGPE: Addressing Domain Gaps and Pose Errors for Robust Collaborative 3D Object Detectioncited by 3
  17. 2025CoBEVMoE: Heterogeneity-aware Feature Fusion with Dynamic Mixture-of-Experts for Collaborative Perceptioncited by 3
  18. 2023An End-to-End Framework of Road User Detection, Tracking, and Prediction from Monocular Imagescited by 2
  19. 2024Self-Localized Collaborative Perceptioncited by 2
  20. 2024StreamLTS: Query-based Temporal-Spatial LiDAR Fusion for Cooperative Object Detectioncited by 2
  21. 2024MR3D-Net: Dynamic Multi-Resolution 3D Sparse Voxel Grid Fusion for LiDAR-Based Collective Perceptioncited by 2
  22. 2024Channel-Aware Throughput Maximization for Cooperative Data Fusion in CAVcited by 2
  23. 2026COOPERTRIM: Adaptive Data Selection for Uncertainty-Aware Cooperative Perceptioncited by 2
  24. 2024Cooperative Visual-LiDAR Extrinsic Calibration Technology for Intersection Vehicle-Infrastructure: A reviewcited by 1
  25. 2025Coop-WD: Cooperative Perception with Weighting and Denoising for Robust V2V Communicationcited by 1
  26. 2023Cooperative Saliency-based Obstacle Detection and AR Rendering for Increased Situational Awarenesscited by 0
  27. 2024CoSense3D: an Agent-based Efficient Learning Framework for Collective Perceptioncited by 0
  28. 2025ChatStitch: Visualizing Through Structures via Surround-View Unsupervised Deep Image Stitching with Collaborative LLM-Agentscited by 0
  29. 2025DenoiseCP-Net: Efficient Collective Perception in Adverse Weather via Joint LiDAR-Based 3D Object Detection and Denoisingcited by 0
  30. 2025Communication-Efficient Multi-Agent 3D Detection via Hybrid Collaborationcited by 0
  31. 2026Robust Fusion of Object-Level V2X for Learned 3D Object Detectioncited by 0
  32. 2026Adversarial Trust Poisoning in Vehicular Collaborative Perceptioncited by 0
  33. 2026VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulationcited by 0