mlsanityData to 14 Oct 2026

Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps

arXiv 2209.12836 ↗First posted 26 Sep 2022cs.CVcited by 255

Not on the map. Why?

Abstract (arXiv)

Multi-agent collaborative perception could significantly upgrade the perception performance by enabling agents to share complementary information with each other through communication. It inevitably results in a fundamental trade-off between perception performance and communication bandwidth. To tackle this bottleneck issue, we propose a spatial confidence map, which reflects the spatial heterogeneity of perceptual information. It empowers agents to only share spatially sparse, yet perceptually critical information, contributing to where to communicate. Based on this novel spatial confidence map, we propose Where2comm, a communication-efficient collaborative perception framework. Where2comm has two distinct advantages: i) it considers pragmatic compression and uses less communication to achieve higher perception performance by focusing on perceptually critical areas; and ii) it can handle varying communication bandwidth by dynamically adjusting spatial areas involved in communication. To evaluate Where2comm, we consider 3D object detection in both real-world and simulation scenarios with two modalities (camera/LiDAR) and two agent types (cars/drones) on four datasets: OPV2V, V2X-Sim, DAIR-V2X, and our original CoPerception-UAVs. Where2comm consistently outperforms previous methods; for example, it achieves more than 100,000 × lower communication volume and still outperforms DiscoNet and V2X-ViT on OPV2V. Our code is available at https://github.com/MediaBrain-SJTU/where2comm.

Key facts. Cited by 255 papers in the map (data through 14 Oct 2026). Builds on 27 of its 52 references that are in the map. First posted on arXiv 26 Sep 2022.

Builds on

27 of 52 references.

References · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  5. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  6. 2019Objects as Pointscited by 1,175
  7. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  8. 2017Deep Layer Aggregationcited by 436
  9. 2016Learning Multiagent Communication with Backpropagationcited by 366
  10. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  11. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  12. 2021OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communicationcited by 304
15 more
  1. 2020V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Predictioncited by 292
  2. 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 273
  3. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  4. 2021Learning Distilled Collaboration Graph for Multi-Agent Perceptioncited by 194
  5. 2020When2com: Multi-Agent Perception via Communication Graph Groupingcited by 157
  6. 2020Who2com: Collaborative Perception via Learnable Handshake Communicationcited by 127
  7. 2018Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Taskscited by 121
  8. 2019Cooperative Perception for 3D Object Detection in Driving Scenarios using Infrastructure Sensorscited by 110
  9. 2020MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Mapscited by 100
  10. 2022Latency-Aware Collaborative Perceptioncited by 86
  11. 20203D Point Cloud Processing and Learning for Autonomous Drivingcited by 68
  12. 2017VAIN: Attentional Multi-agent Predictive Modelingcited by 53
  13. 2022Uncertainty Quantification of Collaborative Detection for Self-Drivingcited by 46
  14. 2022Multi-Robot Collaborative Perception with Graph Neural Networkscited by 35
  15. 2022Aerial Monocular 3D Object Detectioncited by 23

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 37; 2024: 54; 2025: 81; 2026: 79.

255 papers.

Sort:

By area:

  1. 2022Robust Collaborative 3D Object Detection in Presence of Pose Errorscited by 129
  2. 2023V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecastingcited by 114
  3. 2023Collaborative Perception in Autonomous Driving: Methods, Datasets and Challengescited by 87
  4. 2024An Extensible Framework for Open Heterogeneous Collaborative Perceptioncited by 87
  5. 2023Collaboration Helps Camera Overtake LiDAR in 3D Detectioncited by 81
  6. 2023HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformercited by 70
  7. 2024Communication-Efficient Collaborative Perception via Information Filling with Codebookcited by 68
  8. 2023Asynchrony-Robust Collaborative Perception via Bird's Eye View Flowcited by 58
  9. 2023Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perceptioncited by 52
  10. 2023Synthetic Datasets for Autonomous Driving: A Surveycited by 48
  11. 2022Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communicationcited by 47
  12. 2024V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Modelscited by 47
38 more
  1. 2025STAMP: Scalable Task And Model-agnostic Collaborative Perceptioncited by 44
  2. 2024End-to-End Autonomous Driving through V2X Cooperationcited by 42
  3. 2023CORE: Cooperative Reconstruction for Multi-Agent Perceptioncited by 41
  4. 2024AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learningcited by 40
  5. 2023Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perceptioncited by 38
  6. 2024RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perceptioncited by 38
  7. 2023DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detectioncited by 34
  8. 2024Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehiclescited by 33
  9. 2024Collaborative Perception for Connected and Autonomous Driving: Challenges, Possible Solutions and Opportunitiescited by 32
  10. 2023Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 31
  11. 2024V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Predictioncited by 31
  12. 2023TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Drivingcited by 30
  13. 2023UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Frameworkcited by 29
  14. 2022V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perceptioncited by 28
  15. 2025CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridizationcited by 28
  16. 2023Collaborative Multi-Object Tracking with Conformal Uncertainty Propagationcited by 27
  17. 2025V2V-LLM: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multimodal Large Language Modelscited by 27
  18. 2023Vehicle-Infrastructure Cooperative 3D Object Detection via Feature Flow Predictioncited by 25
  19. 2023Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Drivingcited by 25
  20. 2023QUEST: Query Stream for Practical Cooperative Perceptioncited by 23
  21. 2023Open-sourced Data Ecosystem in Autonomous Driving: the Present and Futurecited by 23
  22. 2023Learning Cooperative Trajectory Representations for Motion Forecastingcited by 21
  23. 2023BM2CP: Efficient Collaborative Perception with LiDAR-Camera Modalitiescited by 20
  24. 2024Towards Collaborative Autonomous Driving: Simulation Platform and End-to-End Systemcited by 20
  25. 2023Adaptive Communications in Collaborative Perception with Domain Alignment for Autonomous Drivingcited by 19
  26. 2023S2R-ViT for Multi-Agent Cooperative Perception: Bridging the Gap from Simulation to Realitycited by 18
  27. 2024V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detectioncited by 18
  28. 2023DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perceptioncited by 17
  29. 2023AccidentGPT: Accident Analysis and Prevention from V2X Environmental Perception with Multi-modal Large Modelcited by 17
  30. 2024UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehiclescited by 16
  31. 2023Vehicle-to-Everything Cooperative Perception for Autonomous Drivingcited by 15
  32. 2024One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perceptioncited by 15
  33. 2025Griffin: Aerial-Ground Cooperative Detection and Tracking Dataset and Benchmarkcited by 15
  34. 2025SparseAlign: A Fully Sparse Framework for Cooperative Object Detectioncited by 15
  35. 2025TraF-Align: Trajectory-aware Feature Alignment for Asynchronous Multi-agent Perceptioncited by 15
  36. 2025UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perceptioncited by 15
  37. 2024Directed-CP: Directed Collaborative Perception for Connected and Autonomous Vehicles via Proactive Attentioncited by 14
  38. 2025Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directionscited by 14

50 most cited of 255 All 255 (JSON)