Skip to content

ideal_scenarios_methods.md

Latest commit

 

History

History
135 lines (126 loc) · 20.8 KB

ideal_scenarios_methods.md

File metadata and controls

135 lines (126 loc) · 20.8 KB

A summary of state-of-the-art collaborative perception methods for ideal scenarios

Table

Method Venue Modality Scheme Data Fusion Comm Mecha Feat Fusion Loss Func Code
Cooper [1] ICDCS'19 LiDAR E Raw - - - -
F-Cooper [2] SEC'19 LiDAR I - - Trad - Linkn
Who2com [3] ICRA'20 Camera I - Agent Trad - -
When2com [4] CVPR'20 Camera I - Agent Trad - Linkn
V2VNet [5] ECCV'20 LiDAR I - - Graph - -
Coop3D [6] TITS'20 LiDAR E, L Raw, Out - - - Linkn
CoFF [7] IoT'21 LiDAR I - - Trad - -
DiscoNet [8] NeurIPS'21 LiDAR I Raw - Graph - Linkc
MP-Pose [9] RAL'22 Camera I - - Graph - -
FPV-RCNN [10] RAL'22 LiDAR I Out Feat Trad - Linkn
AttFusion [11] ICRA'22 LiDAR I - - Atten - Linko
TCLF [12] CVPR'22 LiDAR L Out - - - Linkv
COOPERNAUT [13] CVPR'22 LiDAR I - - Atten - Linkn
V2X-ViT [14] ECCV'22 LiDAR I - - Atten - Linko
CRCNet [15] MM'22 LiDAR I - - Atten Redund -
CoBEVT [16] CoRL'22 Camera I - - Atten - Linko
Where2comm [17] NeurIPS'22 LiDAR I - Agent, Feat Atten - Linko
Double-M [18] ICRA'23 LiDAR E, I, L - - - Uncert Linkc
CoCa3D [19] CVPR'23 Camera I - Feat Trad - Linko
HM-ViT [20] ICCV'23 LiDAR, Camera I - - Atten - Linko
CORE [21] ICCV'23 LiDAR I Raw Feat Atten Recon Linko
SCOPE [22] ICCV'23 LiDAR I - - Atten (ST) - Linko
TransIFF [23] ICCV'23 LiDAR I - Feat Atten - -
UMC [24] ICCV'23 LiDAR I - Feat Graph - Linkc
HYDRO-3D [25] TIV'23 LiDAR I - - Atten (ST) - -
MKD-Cooper [26] TIV'23 LiDAR I Raw - Atten - Linko
V2VFormer++ [27] TITS'23 LiDAR, Camera I - - Atten - -
How2comm [28] NeurIPS'23 LiDAR I - Feat Atten (ST) - Linko
What2comm [29] MM'23 LiDAR I - Feat Atten (ST) - -
BM2CP [30] CoRL'23 LiDAR, Camera I - Feat Atten - Linko
DI-V2X [31] AAAI'24 LiDAR I Raw Feat Atten - Linko
QUEST [32] ICRA'24 Camera I, L - Feat Atten - -
CMiMC [33] AAAI'24 LiDAR I - Feat - ✔️ Linkc
Select2Col [34] TVT'24 LiDAR I - Agent Atten (ST) - Linko
MOT-CUP [35] RAL'24 LiDAR E, I, L - - - Uncert Linkc
CodeFilling [36] CVPR'24 LiDAR, Camera I - Feat Trad - Linko
IFTR [37] ECCV'24 Camera I - Feat Atten - Linko
VIMI [38] ICRA'24 Camera I - - Atten - Linkv
CPPC [39] ICLR'25 LiDAR I - Feat Trad - -
CoSDH [40] CVPR'25 LiDAR I, L - Feat Trad - Linko
CoGMP [41] CVPR'25 Camera I - Feat Trad - -
CoST [42] ICCV'25 LiDAR I - Feat Atten (ST) - -
V2XPnP [43] ICCV'25 LiDAR I - Feat Atten (ST) - Linko
mmCooper [44] ICCV'25 LiDAR I, L - Feat Atten - Linko
GSCOOP [45] ICCV'25 Camera I - Gaussian Trad - -
RayFusion [46] NeurIPS'25 Camera I - Feat+Ray Trad - -
InfoCom [47] AAAI'26 LiDAR I - Feat Trad - -
SparseCoop [48] AAAI'26 Camera I - Feat Atten (ST) - -
ZeRCP [49] AAAI'26 Camera I - Feat Atten (ST) - -
DiGS-CP [50] AAAI'26 LiDAR I - Feat Atten (ST) - Linko
CooperTrim [51] ICLR'26 LiDAR, Camera I - Feat Atten - -
RDcomm [52] ICLR'26 LiDAR, Camera I - Feat Trad - -
SiMO [53] ICLR'26 LiDAR + Camera I - - Atten - Linko]

Note:

  • Schemes include early (E), intermediate (I) and late (L) collaboration.
  • Data Fusion: data fusion includes raw data fusion (Raw) and output fusion (Out).
  • Comm Mecha: communication mechanism includes agent selection (Agent) and feature selection (Feat).
  • Feat Fusion: feature fusion can be divided into traditional (Trad), graph-based (Graph) and attention-based (Atten) feature fusion. （ST: spatio-temporal）
  • Loss Func: loss function can be used for uncertainty estimation (Uncert), redundancy minimization (Redund) and Reconstruction (Recon), etc.
  • Code Framework: o (OpenCOOD), v (VIC3D), c (CoPerception), n (Non-mainstream framework)

Back to Contents 🔙

References

Published

  1. Cooper: Cooperative perception for connected autonomous vehicles based on 3d point clouds (ICDCS'19) [pdf]
  2. F-Cooper: Feature based cooperative perception for autonomous vehicle edge computing system using 3D point clouds (SEC'19) [pdf]
  3. Who2com: Collaborative perception via learnable handshake communication (ICRA'20) [pdf]
  4. When2com: Multi-agent perception via communication graph grouping (CVPR'20) [pdf]
  5. V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction (ECCV'20) [pdf]
  6. Cooperative perception for 3D object detection in driving scenarios using infrastructure sensors (TITS'20) [pdf]
  7. CoFF: Cooperative spatial feature fusion for 3-d object detection on autonomous vehicles (IoT'21) [pdf]
  8. Learning distilled collaboration graph for multi-agent perception (NeurIPS'21) [pdf] [code]
  9. Multi-Robot Collaborative Perception with Graph Neural Networks (RAL'22) [pdf]
  10. Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving (RAL'22) [pdf] [code]
  11. OPV2V: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication (ICRA'22) [pdf] [code]
  12. DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection (CVPR'22) [pdf] [code]
  13. COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles (CVPR'22) [pdf] [code]
  14. V2X-ViT: Vehicle-to-everything cooperative perception with vision transformer (ECCV'22) [pdf] [code]
  15. Complementarity-Enhanced and Redundancy-Minimized Collaboration Network for Multi-agent Perception (MM'22) [pdf]
  16. CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers (CoRL'22) [pdf] [code]
  17. Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps (NeurIPS'22) [pdf] [code]
  18. Uncertainty Quantification of Collaborative Detection for Self-Driving (ICRA'23) [pdf] [code]
  19. Collaboration Helps Camera Overtake LiDAR in 3D Detection (CVPR'23) [pdf] [code]
  20. HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer (ICCV'23) [pdf]
  21. CORE: Cooperative Reconstruction for Multi-Agent Perception (ICCV'23) [pdf] [code]
  22. Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception (ICCV'23) [pdf] [code]
  23. TransIFF: An Instance-Level Feature Fusion Framework for Vehicle-Infrastructure Cooperative 3D Detection with Transformers (ICCV'23) [pdf]
  24. UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework (ICCV'23) [pdf] [code]
  25. HYDRO-3D: Hybrid Object Detection and Tracking for Cooperative Perception Using 3D LiDAR (TIV'23) [pdf]
  26. MKD-Cooper: Cooperative 3D Object Detection for Autonomous Driving via Multi-teacher Knowledge Distillation (TIV'23) [pdf] [code]
  27. V2VFormer ++ : Multi-Modal Vehicle-to-Vehicle Cooperative Perception via Global-Local Transformer (TITS'23) [pdf]
  28. How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception (NeurIPS'23) [pdf] [code]
  29. What2comm: Towards Communication-efficient Collaborative Perception via Feature Decoupling (MM'23) [pdf]
  30. BM2CP: Efficient Collaborative Perception with LiDAR-Camera Modalities (CoRL'23) [pdf] [code]
  31. DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection (AAAI'24) [pdf] [code]
  32. QUEST: Query Stream for Practical Cooperative Perception (ICRA'24) [pdf]
  33. What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception (AAAI'24) [pdf] [code]
  34. Select2Col: Leveraging Spatial-Temporal Importance of Semantic Information for Efficient Collaborative Perception (TVT'24) [pdf] [code]
  35. Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation (RAL'24) [pdf] [code]
  36. Communication-Efficient Collaborative Perception via Information Filling with Codebook (CVPR'24) [pdf] [code]
  37. IFTR: An Instance-Level Fusion Transformer for Visual Collaborative Perception (ECCV'24) [pdf] [code]
  38. EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection (ICRA'24) [pdf] [code]
  39. Point Cluster: A Compact Message Unit for Communication-Efficient Collaborative Perception (ICLR'25) [pdf]
  40. CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization (CVPR'25) [pdf] [code]
  41. Generative Map Priors for Collaborative BEV Semantic Segmentation (CVPR'25) [pdf]
  42. CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective (ICCV'25) [pdf]
  43. V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction (ICCV'25) [pdf] [code]
  44. mmCooper: A Multi-agent Multi-stage Communication-efficient and Collaboration-robust Cooperative Perception Framework (ICCV'25) [pdf] [code]
  45. Communication-Efficient Multi-Vehicle Collaborative Semantic Segmentation via Sparse 3D Gaussian Sharing (ICCV'25) [pdf]
  46. RayFusion: Ray Fusion Enhanced Collaborative Visual Perception (NeurIPS'25) [pdf]
  47. InfoCom: Kilobyte-Scale Communication-Efficient Collaborative Perception with Information Bottleneck (AAAI'26) [pdf]
  48. SparseCoop: Cooperative Perception with Kinematic-Grounded Queries (AAAI'26) [pdf]
  49. ZeRCP: Towards Communication-Efficient Collaborative Perception and Future Scene Prediction via Request-Free Spatial Filtering (AAAI'26) [pdf]
  50. From Discriminative to Generative: A Diffusion-Based Paradigm for Multi-Agent Collaborative Perception (AAAI'26) [pdf] [code]
  51. CooperTrim: Adaptive Data Selection for Uncertainty-Aware Cooperative Perception (ICLR'26) [pdf]
  52. Rate-Distortion Optimized Communication for Collaborative Perception (ICLR'26) [pdf]
  53. SiMO: Single-Modality-Operable Multimodal Collaborative Perception (ICLR'26) [pdf] [code]