├── Figures ├── fig1.jpeg ├── fig2.jpeg ├── fig3.jpeg ├── fig4.jpeg ├── fig5.jpeg ├── fig6.jpeg └── overview.png ├── README.md ├── dataset_summary.md ├── ideal_scenarios_methods.md ├── new_trends.md └── real_world_methods.md /Figures/fig1.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatOneTwo/Collaborative-Perception-in-Autonomous-Driving/c9490c2816dbea5da0366685d64d587119355ac8/Figures/fig1.jpeg -------------------------------------------------------------------------------- /Figures/fig2.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatOneTwo/Collaborative-Perception-in-Autonomous-Driving/c9490c2816dbea5da0366685d64d587119355ac8/Figures/fig2.jpeg -------------------------------------------------------------------------------- /Figures/fig3.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatOneTwo/Collaborative-Perception-in-Autonomous-Driving/c9490c2816dbea5da0366685d64d587119355ac8/Figures/fig3.jpeg -------------------------------------------------------------------------------- /Figures/fig4.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatOneTwo/Collaborative-Perception-in-Autonomous-Driving/c9490c2816dbea5da0366685d64d587119355ac8/Figures/fig4.jpeg -------------------------------------------------------------------------------- /Figures/fig5.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatOneTwo/Collaborative-Perception-in-Autonomous-Driving/c9490c2816dbea5da0366685d64d587119355ac8/Figures/fig5.jpeg -------------------------------------------------------------------------------- /Figures/fig6.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatOneTwo/Collaborative-Perception-in-Autonomous-Driving/c9490c2816dbea5da0366685d64d587119355ac8/Figures/fig6.jpeg -------------------------------------------------------------------------------- /Figures/overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatOneTwo/Collaborative-Perception-in-Autonomous-Driving/c9490c2816dbea5da0366685d64d587119355ac8/Figures/overview.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Collaborative Perception in Autonomous Driving Survey 2 | 3 | This repo is constructed for collecting and categorizing papers about collaborative perception according to our ITSM survey paper: 4 | ***Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges*** [[arXiv](https://arxiv.org/abs/2301.06262)] [[ITSM](https://ieeexplore.ieee.org/document/10248946)] [[Zhihu](https://zhuanlan.zhihu.com/p/644931857)] 5 | 6 |

7 | 8 |

9 | 10 |
11 |

12 | Methods | 13 | Datasets | 14 | Challenges 15 |

16 |
17 | 18 | 19 | 20 | 21 | ## Methods 22 | ### Methods for Ideal Scenarios 23 | - Raw data fusion 24 | - Customized communication mechanism 25 | - Feature fusion 26 | - Customized loss function 27 | - Output fusion 28 | 29 | 👉 View details in [**Methods for Ideal Scenarios**](ideal_scenarios_methods.md) 30 | 31 | ### Methods for Real-world Issues 32 | - Localization errors 33 | - Communication issues 34 | - Model or task discrepancies 35 | - Privacy and security issues 36 | 37 | 👉 View details in [**Methods for Real-World Issues**](real_world_methods.md) 38 | 39 | 40 | ## Datasets 41 | - Real-world or Simulator 42 | - V2V or V2I 43 | 44 | 👉 View details in [**Datasets Summary**](dataset_summary.md) 45 | 46 | ## Challenges 47 | - Transmission Efficiency in Collaborative Perception 48 | - Collaborative Perception in Complex Scenes 49 | - Federated Learning-based Collaborative Perception 50 | - Collaborative Perception with Low Labeling Dependence 51 | 52 | 👉 View details in [**New Trends**](new_trends.md) 53 | 54 | ## Citation 55 | If you find this work useful, please cite our paper: 56 | ``` 57 | @article{han2023collaborative, 58 | author={Han, Yushan and Zhang, Hui and Li, Huifang and Jin, Yi and Lang, Congyan and Li, Yidong}, 59 | journal={IEEE Intelligent Transportation Systems Magazine}, 60 | title={Collaborative Perception in Autonomous Driving: Methods, Datasets, and Challenges}, 61 | year={2023}, 62 | volume={15}, 63 | number={6}, 64 | pages={131-151}, 65 | doi={10.1109/MITS.2023.3298534}} 66 | 67 | ``` 68 | 69 | -------------------------------------------------------------------------------- /dataset_summary.md: -------------------------------------------------------------------------------- 1 | # A summary of large-scale collaborative perception datasets 2 | 3 | **Usage of Common Datasets** (from papers with code): 4 | - [V2X-SIM](https://paperswithcode.com/dataset/v2x-sim) | [OPV2V](https://paperswithcode.com/dataset/opv2v) | [V2XSet](https://paperswithcode.com/dataset/v2xset) | [DAIR-V2X](https://paperswithcode.com/dataset/dair-v2x) | [V2V4Real](https://paperswithcode.com/dataset/v2v4real) | [DAIR-V2X-Seq](https://paperswithcode.com/dataset/dair-v2x-seq) 5 | 6 | 7 | | **Dataset** | **Venue** | **Source** | **Frame** | **V2V** | **V2I** | **I2I** | **Agents** | **Camera** | **LiDAR** | **Depth** | **OD** | **SS** | **OT** | **MP** | **Website** | 8 | |:----------------:|:---------:|:----------:|:---------:|:--------:|:--------:|:----------:|:----------:|:----------:|:---------:|:---------:|:---------:|:---------:|:---------:|:---------:|:----------------------------------------------------:| 9 | | V2V-Sim [1] | ECCV'20 | Simu | 51K | ✔ | - | - | 1-7 | - | ✔ | - | ✔ | - | - | ✔ | - | 10 | | V2X-Sim [2] | RAL'21 | Simu | 10k | ✔ | ✔ | - |1-5 | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | - | [Link](https://ai4ce.github.io/V2X-Sim) | 11 | | OPV2V [3] | ICRA'22 | Simu | 11K | ✔ | - | - |1-7 | ✔ | ✔ | - | ✔ | ✔ | - | - | [Link](https://mobility-lab.seas.ucla.edu/opv2v) | 12 | | DAIR-V2X-C [4] | CVPR'22 | Real | 39k | - | ✔ | - |2 | ✔ | ✔ | - | ✔ | - | - | - | [Link](https://thudair.baai.ac.cn/coop-dtest) | 13 | | V2XSet [5] | ECCV'22 | Simu | 11K | ✔ | ✔ | - |2-5 | ✔ | ✔ | - | ✔ | - | - | - | [Link](https://github.com/DerrickXuNu/v2x-vit) | 14 | | DOLPHINS [6] | ACCV'22 | Simu | 42k | ✔ | ✔ | - |3 | ✔ | ✔ | - | ✔ | - | - | - | [Link](https://dolphins-dataset.net) | 15 | | V2V4Real [7] | CVPR'23 | Real | 20K | ✔ | - | - |2 | ✔ | ✔ | - | ✔ | - | ✔ | - | [Link](https://mobility-lab.seas.ucla.edu/v2v4real/) | 16 | | V2X-Seq [8] | CVPR'23 | Real | 15k | - | ✔ | - |2 | ✔ | ✔ | - | ✔ | - | ✔ | ✔ | [Link](https://thudair.baai.ac.cn/coop-forecast) | 17 | | DeepAccident [9] | AAAI'24 | Simu | 57K | ✔ | ✔ | - |1-5 | ✔ | ✔ | - | ✔ | ✔ | ✔ | ✔ | [Link](https://deepaccident.github.io/index.html) | 18 | | HoloVIC [10] | CVPR'24 | Real | 100K | - | ✔ | - |2 | ✔ | ✔ | - | ✔ | - | ✔ | - | [Link](https://holovic.net/) | 19 | | TUMTraf-V2X [11] | CVPR'24 | Real | 2K | - | ✔ | - |2 | ✔ | ✔ | - | ✔ | - | ✔ | - | [Link](https://tum-traffic-dataset.github.io/tumtraf-v2x/) | 20 | | R-Cooper [12] | CVPR'24 | Real | 30K | - | - | ✔ | 2 | ✔ | ✔ | - | ✔ | - | ✔ | - | [Link](https://tum-traffic-dataset.github.io/tumtraf-v2x/) | 21 | | MARS [13] | CVPR'24 | Real | 1.5k | ✔ | - | - |2-3 | ✔ | ✔ | - | -| - |-| - | [Link](https://ai4ce.github.io/MARS/) | 22 | | V2X-Real [14] | ECCV'24 | Real | 33k | ✔ | ✔ | ✔ |2-4 | ✔ | ✔ | - | ✔ | - |-| - | [Link](https://github.com/ucla-mobility/V2X-Real) | 23 | 24 | Notes: 25 | - Source: simulator (Simu) and real-world (Real). 26 | - Frame refers to annotated LiDAR-based cooperative perception frame number. 27 | - Supported common perception tasks: 3D object detection (OD), BEV semantic segmentation (SS), 3D object tracking (OT), motion prediction (MP). 28 | 29 | 30 | Back to [Contents](README.md) 🔙 31 | 32 | References: 33 | 1. [V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction](https://arxiv.org/abs/2008.07519) (ECCV'20) 34 | 2. [V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving](https://arxiv.org/abs/2202.08449) (RAL'21) 35 | 3. [OPV2V: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication](https://arxiv.org/abs/2109.07644) (ICRA'22) 36 | 4. [DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection](https://arxiv.org/abs/2204.05575) (CVPR'22) 37 | 5. [V2X-ViT: Vehicle-to-everything cooperative perception with vision transformer](https://arxiv.org/abs/2203.10638) (ECCV'22) 38 | 6. [DOLPHINS: Dataset for Collaborative Perception enabled Harmonious and Interconnected Self-driving](https://arxiv.org/abs/2207.07609) (ACCV'22) 39 | 7. [V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception](https://arxiv.org/abs/2303.07601) (CVPR'23) 40 | 8. [V2X-Seq: A large-scale sequential dataset for vehicle-infrastructure cooperative perception and forecasting](https://arxiv.org/abs/2305.05938) (CVPR'23) 41 | 9. [DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving](https://arxiv.org/abs/2304.01168) (AAAI'24) 42 | 10. [HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative](https://arxiv.org/abs/2403.02640) (CVPR'24) 43 | 11. [TUMTraf V2X Cooperative Perception Dataset](https://arxiv.org/abs/2403.01316) (CVPR'24) 44 | 12. [RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception](https://arxiv.org/abs/2403.10145) (CVPR'24) 45 | 13. [Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset](https://openaccess.thecvf.com/content/CVPR2024/papers/Li_Multiagent_Multitraversal_Multimodal_Self-Driving_Open_MARS_Dataset_CVPR_2024_paper.pdf) (CVPR'24) 46 | 14. [V2X-Real: a Largs-Scale Dataset for Vehicle-to-Everything Cooperative Perception](https://arxiv.org/abs/2403.16034) (ECCV'24) 47 | 48 | -------------------------------------------------------------------------------- /ideal_scenarios_methods.md: -------------------------------------------------------------------------------- 1 | # A summary of state-of-the-art collaborative perception methods for ideal scenarios 2 | 3 |
4 |

5 | Table | 6 | Refer 7 |

8 |
9 | 10 | ## Table 11 | | Method | Venue | Modality | Scheme | Data Fusion | Comm Mecha | Feat Fusion | Loss Func | Code | 12 | |:-----------------:|:----------:|:-------------:|:------------:|:-----------------:|:----------------:|:-----------------:|:---------------:|:------------------------------------------------------------------:| 13 | | Cooper [1] | ICDCS'19 | LiDAR | E | Raw | - | - | - | - | 14 | | F-Cooper [2] | SEC'19 | LiDAR | I | - | - | Trad | - | [Linkn](https://github.com/Aug583/F-COOPER) | 15 | | Who2com [3] | ICRA'20 | Camera | I | - | Agent | Trad | - | - | 16 | | When2com [4] | CVPR'20 | Camera | I | - | Agent | Trad | - | [Linkn](https://github.com/GT-RIPL/MultiAgentPerception) | 17 | | V2VNet [5] | ECCV'20 | LiDAR | I | - | - | Graph | - | - | 18 | | Coop3D [6] | TITS'20 | LiDAR | E, L | Raw, Out | - | - | - | [Linkn](https://github.com/eduardohenriquearnold/coop-3dod-infra) | 19 | | CoFF [7] | IoT'21 | LiDAR | I | - | - | Trad | - | - | 20 | | DiscoNet [8] | NeurIPS'21 | LiDAR | I | Raw | - | Graph | - | [Linkc](https://github.com/ai4ce/DiscoNet) | 21 | | MP-Pose [9] | RAL'22 | Camera | I | - | - | Graph | - | - | 22 | | FPV-RCNN [10] | RAL'22 | LiDAR | I | Out | Feat | Trad | - | [Linkn](https://github.com/YuanYunshuang/FPV_RCNN) | 23 | | AttFusion [11] | ICRA'22 | LiDAR | I | - | - | Atten | - | [Linko](https://github.com/DerrickXuNu/OpenCOOD) | 24 | | TCLF [12] | CVPR'22 | LiDAR | L | Out | - | - | - | [Linkv](https://github.com/AIR-THU/DAIR-V2X) | 25 | | COOPERNAUT [13] | CVPR'22 | LiDAR | I | - | - | Atten | - | [Linkn](https://github.com/UT-Austin-RPL/Coopernaut) | 26 | | V2X-ViT [14] | ECCV'22 | LiDAR | I | - | - | Atten | - | [Linko](https://github.com/DerrickXuNu/v2x-vit) | 27 | | CRCNet [15] | MM'22 | LiDAR | I | - | - | Atten | Redund | - | 28 | | CoBEVT [16] | CoRL'22 | Camera | I | - | - | Atten | - | [Linko](https://github.com/DerrickXuNu/CoBEVT) | 29 | | Where2comm [17] | NeurIPS'22 | LiDAR | I | - | Agent, Feat | Atten | - | [Linko](https://github.com/MediaBrain-SJTU/Where2comm) | 30 | | Double-M [18] | ICRA'23 | LiDAR | E, I, L | - | - | - | Uncert | [Linkc](https://github.com/coperception/double-m-quantification) | 31 | | CoCa3D [19] | CVPR'23 | Camera | I | - | Feat | Trad | - | [Linko](https://github.com/MediaBrain-SJTU/CoCa3D) | 32 | | HM-ViT [20] | ICCV'23 | LiDAR, Camera | I | - | - | Atten | - | [Linko](https://github.com/XHwind/HM-ViT) | 33 | | CORE [21] | ICCV'23 | LiDAR | I | Raw | Feat | Atten | Recon | [Linko](https://github.com/zllxot/CORE) | 34 | | SCOPE [22] | ICCV'23 | LiDAR | I | - | - | Atten (ST) | - | [Linko](https://github.com/starfdu1418/SCOPE) | 35 | | TransIFF [23] | ICCV'23 | LiDAR | I | - | Feat | Atten | - | - 36 | | UMC [24] | ICCV'23 | LiDAR | I | - | Feat |Graph | - | [Linkc](https://github.com/ispc-lab/UMC) | 37 | | HYDRO-3D [25] | TIV'23 | LiDAR | I | - | - |Atten (ST) | - | - | 38 | | MKD-Cooper [26] | TIV'23 | LiDAR | I | Raw | - |Atten | - | [Linko](https://github.com/EricLee523/MKD-Cooper)| 39 | | V2VFormer++ [27] | TITS'23 | LiDAR, Camera | I | - | - |Atten | - | - | 40 | | How2comm [28] | NeurIPS'23 | LiDAR | I | - | Feat |Atten (ST) | - | [Linko](https://github.com/ydk122024/How2comm)| 41 | | What2comm [29] | MM'23 | LiDAR | I | - | Feat |Atten (ST) | - | - | 42 | | BM2CP [30] | CoRL'23 | LiDAR, Camera | I | - | Feat |Atten | - | [Linko](https://github.com/byzhaoAI/BM2CP) | 43 | | DI-V2X [31] | AAAI'24 | LiDAR | I | Raw | Feat |Atten | - | [Linko](https://github.com/Serenos/DI-V2X) | 44 | | QUEST [32] | ICRA'24 | Camera | I, L | - | Feat |Atten | - | - | 45 | | CMiMC [33] | AAAI'24 | LiDAR | I | - | Feat |- | ✔️ | [Linkc](https://github.com/77SWF/CMiMC)| 46 | | Select2Col [34] | TVT'24 | LiDAR | I | - | Agent |Atten (ST) | - | [Linko](https://github.com/huangqzj/select2col) | 47 | | MOT-CUP [35] | RAL'24 | LiDAR | E, I, L | - | - |- | Uncert | [Linkc](https://github.com/susanbao/mot_cup) | 48 | | CodeFilling [36] | CVPR'24 | LiDAR, Camera | I | - | Feat | Trad | - | [Linko](https://github.com/PhyllisH/CodeFilling) | 49 | | IFTR [37] | ECCV'24 | Camera | I | - | Feat | Atten | - | [Linko](https://github.com/wangsh0111/IFTR) | 50 | | VIMI [38] | ICRA'24 | Camera | I | - | - | Atten | - | [Linkv](https://github.com/Bosszhe/EMIFF) | 51 | | CPPC [39] | ICLR'25 | LiDAR | I | - | Feat | Trad | - | - | 52 | | CoSDH [40] | CVPR'25 | LiDAR | I, L | - | Feat | Trad | - | [Linko](https://github.com/Xu2729/CoSDH) | 53 | | CoGMP [41] | CVPR'25 | Camera | I | - | Feat | Trad | - | - | 54 | 55 | 56 | Note: 57 | - Schemes include early (E), intermediate (I) and late (L) collaboration. 58 | - **Data Fusion**: data fusion includes raw data fusion (**Raw**) and output fusion (**Out**). 59 | - **Comm Mecha**: communication mechanism includes agent selection (**Agent**) and feature selection (**Feat**). 60 | - **Feat Fusion**: feature fusion can be divided into traditional (**Trad**), graph-based (**Graph**) and attention-based (**Atten**) feature fusion. （ST: spatio-temporal） 61 | - **Loss Func**: loss function can be used for uncertainty estimation (**Uncert**), redundancy minimization (**Redund**) and Reconstruction (**Recon**), etc. 62 | - **Code Framework**: o ([OpenCOOD](https://github.com/DerrickXuNu/OpenCOOD)), v ([VIC3D](https://github.com/AIR-THU/DAIR-V2X)), c ([CoPerception](https://github.com/coperception/coperception)), n (Non-mainstream framework) 63 | 64 | Back to [Contents](README.md) 🔙 65 | 66 | ## References 67 | ### Published 68 | 1. Cooper: Cooperative perception for connected autonomous vehicles based on 3d point clouds (ICDCS'19) [[`pdf`](https://arxiv.org/abs/1905.05265)] 69 | 2. F-Cooper: Feature based cooperative perception for autonomous vehicle edge computing system using 3D point clouds (SEC'19) [[`pdf`](https://arxiv.org/abs/1909.06459)] 70 | 3. Who2com: Collaborative perception via learnable handshake communication (ICRA'20) [[`pdf`](https://arxiv.org/abs/2003.09575)] 71 | 4. When2com: Multi-agent perception via communication graph grouping (CVPR'20) [[`pdf`](https://arxiv.org/abs/2006.00176)] 72 | 5. V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction (ECCV'20) [[`pdf`](https://arxiv.org/abs/2008.07519)] 73 | 6. Cooperative perception for 3D object detection in driving scenarios using infrastructure sensors (TITS'20) [[`pdf`](https://arxiv.org/abs/1912.12147)] 74 | 7. CoFF: Cooperative spatial feature fusion for 3-d object detection on autonomous vehicles (IoT'21) [[`pdf`](https://arxiv.org/abs/2009.11975)] 75 | 8. Learning distilled collaboration graph for multi-agent perception (NeurIPS'21) [[`pdf`](https://arxiv.org/abs/2111.00643)] [[`code`](https://github.com/ai4ce/DiscoNet)] 76 | 9. Multi-Robot Collaborative Perception with Graph Neural Networks (RAL'22) [[`pdf`](https://arxiv.org/abs/2201.01760)] 77 | 10. Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving (RAL'22) [[`pdf`](https://arxiv.org/abs/2109.11615)] [[`code`](https://github.com/YuanYunshuang/FPV_RCNN)] 78 | 11. OPV2V: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication (ICRA'22) [[`pdf`](https://arxiv.org/abs/2109.07644)] [[`code`](https://github.com/DerrickXuNu/OpenCOOD)] 79 | 12. DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection (CVPR'22) [[`pdf`](https://arxiv.org/abs/2204.05575)] [[`code`](https://github.com/AIR-THU/DAIR-V2X)] 80 | 13. COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles (CVPR'22) [[`pdf`](https://arxiv.org/abs/2205.02222)] [[`code`](https://github.com/UT-Austin-RPL/Coopernaut)] 81 | 14. V2X-ViT: Vehicle-to-everything cooperative perception with vision transformer (ECCV'22) [[`pdf`](https://arxiv.org/abs/2203.10638)] [[`code`]()] 82 | 15. Complementarity-Enhanced and Redundancy-Minimized Collaboration Network for Multi-agent Perception (MM'22) [[`pdf`](https://dl.acm.org/doi/abs/10.1145/3503161.3548197)] 83 | 16. CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers (CoRL'22) [[`pdf`](https://arxiv.org/abs/2207.02202)] [[`code`](https://github.com/DerrickXuNu/v2x-vit)] 84 | 17. Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps (NeurIPS'22) [[`pdf`](https://arxiv.org/abs/2209.12836)] [[`code`](https://github.com/MediaBrain-SJTU/Where2comm)] 85 | 18. Uncertainty Quantification of Collaborative Detection for Self-Driving (ICRA'23) [[`pdf`](https://arxiv.org/abs/2209.08162)] [[`code`](https://github.com/coperception/double-m-quantification)] 86 | 19. Collaboration Helps Camera Overtake LiDAR in 3D Detection (CVPR'23) [[`pdf`](https://arxiv.org/abs/2303.13560)] [[`code`](https://github.com/MediaBrain-SJTU/CoCa3D)] 87 | 20. HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer (ICCV'23) [[`pdf`](https://arxiv.org/abs/2304.10628)] 88 | 21. CORE: Cooperative Reconstruction for Multi-Agent Perception (ICCV'23) [[`pdf`](https://arxiv.org/abs/2307.11514)] [[`code`](https://github.com/zllxot/CORE)] 89 | 22. Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception (ICCV'23) [[`pdf`](https://arxiv.org/abs/2307.13929)] [[`code`](https://github.com/starfdu1418/SCOPE)] 90 | 23. TransIFF: An Instance-Level Feature Fusion Framework for Vehicle-Infrastructure Cooperative 3D Detection with Transformers (ICCV'23) [[`pdf`](https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_TransIFF_An_Instance-Level_Feature_Fusion_Framework_for_Vehicle-Infrastructure_Cooperative_3D_ICCV_2023_paper.pdf)] 91 | 24. UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework (ICCV'23) [[`pdf`](https://arxiv.org/abs/2303.12400)] [[`code`](https://github.com/ispc-lab/UMC)] 92 | 25. HYDRO-3D: Hybrid Object Detection and Tracking for Cooperative Perception Using 3D LiDAR (TIV'23) [[`pdf`](https://ieeexplore.ieee.org/abstract/document/10148929)] 93 | 26. MKD-Cooper: Cooperative 3D Object Detection for Autonomous Driving via Multi-teacher Knowledge Distillation (TIV'23) [[`pdf`](https://ieeexplore.ieee.org/abstract/document/10236578)] [[`code`](https://github.com/EricLee523/MKD-Cooper)] 94 | 27. V2VFormer ++ : Multi-Modal Vehicle-to-Vehicle Cooperative Perception via Global-Local Transformer (TITS'23) [[`pdf`](https://ieeexplore.ieee.org/document/10265751/)] 95 | 28. How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception (NeurIPS'23) [[`pdf`](https://openreview.net/forum?id=Dbaxm9ujq6)] [[`code`](https://github.com/ydk122024/How2comm)] 96 | 29. What2comm: Towards Communication-efficient Collaborative Perception via Feature Decoupling (MM'23) [[`pdf`](https://dl.acm.org/doi/10.1145/3581783.3611699)] 97 | 30. BM2CP: Efficient Collaborative Perception with LiDAR-Camera Modalities (CoRL'23) [[`pdf`](https://openreview.net/forum?id=uJqxFjF1xWp)] [[`code`](https://github.com/byzhaoAI/BM2CP)] 98 | 31. DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection (AAAI'24) [[`pdf`](https://arxiv.org/abs/2312.15742)] [[`code`](https://github.com/Serenos/DI-V2X)] 99 | 32. QUEST: Query Stream for Practical Cooperative Perception (ICRA'24) [[`pdf`](https://arxiv.org/abs/2308.01804)] 100 | 33. What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception (AAAI'24) [[`pdf`](https://arxiv.org/abs/2403.10068)] [[`code`](https://github.com/77SWF/CMiMC)] 101 | 34. Select2Col: Leveraging Spatial-Temporal Importance of Semantic Information for Efficient Collaborative Perception (TVT'24) [[`pdf`](https://arxiv.org/abs/2307.16517)] [[`code`](https://github.com/huangqzj/select2col)] 102 | 35. Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation (RAL'24) [[`pdf`](https://arxiv.org/abs/2303.14346)] [[`code`](https://github.com/susanbao/mot_cup)] 103 | 36. Communication-Efficient Collaborative Perception via Information Filling with Codebook (CVPR'24) [[`pdf`](https://arxiv.org/abs/2405.04966)] [[`code`](https://github.com/PhyllisH/CodeFilling)] 104 | 37. IFTR: An Instance-Level Fusion Transformer for Visual Collaborative Perception (ECCV'24) [[`pdf`](https://arxiv.org/abs/2407.09857)] [[`code`](https://github.com/wangsh0111/IFTR)] 105 | 38. EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection (ICRA'24) [[`pdf`](https://arxiv.org/abs/2303.10975)] [[`code`](https://github.com/Bosszhe/EMIFF)] 106 | 39. Point Cluster: A Compact Message Unit for Communication-Efficient Collaborative Perception. (ICLR'25) [[`pdf`](https://openreview.net/forum?id=54XlM8Clkg)] 107 | 40. CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization. (CVPR'25) [[`pdf`](https://arxiv.org/abs/2503.03430)] [[`code`](https://github.com/Xu2729/CoSDH)] 108 | 41. Generative Map Priors for Collaborative BEV Semantic Segmentation. (CVPR'25) [[`pdf`](https://openaccess.thecvf.com/content/CVPR2025/papers/Fu_Generative_Map_Priors_for_Collaborative_BEV_Semantic_Segmentation_CVPR_2025_paper.pdf)] 109 | 110 | 111 | 112 | -------------------------------------------------------------------------------- /new_trends.md: -------------------------------------------------------------------------------- 1 | 2 | ## New Trends 3 | - **Label Efficient** 4 | - Unsupervised / Self-supervised learning: CO3 [1] , DOtA [14] 5 | - Weakly / Sparsely supervised learning: SSC3OD [2], CoDTS [11] 6 | - Domain adaption: S2R-ViT [3], DUSA [4], CUDA-X [18] 7 | - Based Others’ Predictions: R&B-POP [17] 8 | - **Model Adaptation** 9 | - MACP [5] 10 | - CoPEFT [13] 11 | - **Open Heterogeneous Collaborative Perception** 12 | - HEAL [6] 13 | - **New Perception Tasks** 14 | - Multi-Object Cooperative Tracking: DMSTrack [7], MOT-CUP [8] 15 | - Collaborative Semantic Occupancy Prediction: CoHFF [9] 16 | - Cooperative Trajectory: V2X-Graph [10] 17 | - **Extreme Environments** 18 | - DSRC [12], MDD [15], RCP-Bench [19] 19 | - **End-to-End Autonomous Driving** 20 | - UniV2X [16] 21 | 22 | ## References 23 | 1. CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving (*ICLR'23*) [[`pdf`](https://arxiv.org/abs/2206.04028)] [[`code`](https://github.com/Runjian-Chen/CO3)] ![](https://img.shields.io/github/stars/Runjian-Chen/CO3) 24 | 2. SSC3OD: Sparsely Supervised Collaborative 3D Object Detection from LiDAR Point Clouds (*SMC'23*) [[`pdf`](https://arxiv.org/abs/2307.00717)] 25 | 3. S2R-ViT for Multi-Agent Cooperative Perception: Bridging the Gap from Simulation to Reality (*arXiv'23*) [[`pdf`](https://arxiv.org/abs/2307.07935)] 26 | 4. DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception (*MM'23*) [[`pdf`](https://dl.acm.org/doi/10.1145/3581783.3611948)] [[`code`](https://github.com/refkxh/DUSA)] ![](https://img.shields.io/github/stars/refkxh/DUSA) 27 | 5. MACP: Efficient Model Adaptation for Cooperative Perception (*WACV'24*) [[`pdf`](https://arxiv.org/abs/2310.16870)] [[`code`](https://github.com/PurdueDigitalTwin/MACP)] ![](https://img.shields.io/github/stars/PurdueDigitalTwin/MACP) 28 | 6. HEAL: An Extensible Framework for Open Heterogeneous Collaborative Perception (*ICLR'24*) [[`pdf`](https://openreview.net/forum?id=KkrDUGIASk)] [[`code`](https://github.com/yifanlu0227/HEAL)] ![](https://img.shields.io/github/stars/yifanlu0227/HEAL) 29 | 7. Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter (*ICRA'24*) [[`pdf`](https://arxiv.org/abs/2309.14655)] [[`code`](https://github.com/eddyhkchiu/DMSTrack)] ![](https://img.shields.io/github/stars/eddyhkchiu/DMSTrack) 30 | 8. Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation (*RAL'24*) [[`pdf`](https://arxiv.org/abs/2303.14346)] [[`code`](https://github.com/susanbao/mot_cup)] ![](https://img.shields.io/github/stars/susanbao/mot_cup) 31 | 9. Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles (*CVPR'24*) [[`pdf`](https://arxiv.org/abs/2402.07635)] [[`code`](https://github.com/rruisong/CoHFF)] ![](https://img.shields.io/github/stars/rruisong/CoHFF) 32 | 10. Learning Cooperative Trajectory Representations for Motion Forecasting (*NeurIPS'24*) [[`pdf`](https://openreview.net/pdf?id=mcY221BgKi)] [[`code`](https://github.com/AIR-THU/V2X-Graph)] ![](https://img.shields.io/github/stars/AIR-THU/V2X-Graph) 33 | 11. CoDTS: Enhancing Sparsely Supervised Collaborative Perception with a Dual Teacher-Student Framework (*AAAI'25*) [[`pdf`](https://arxiv.org/abs/2412.08344)] [[`code`](https://github.com/CatOneTwo/CoDTS)] ![](https://img.shields.io/github/stars/CatOneTwo/CoDTS) 34 | 12. DSRC: Learning Density-insensitive and Semantic-aware Collaborative Representation against Corruptions (*AAAI'25*) [[`pdf`](https://arxiv.org/abs/2412.10739)] [[`code`](https://github.com/Terry9a/DSRC)] ![](https://img.shields.io/github/stars/Terry9a/DSRC) 35 | 13. CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-Tuning (*AAAI'25*) [[`pdf`](https://arxiv.org/abs/2502.10705)] [[`code`](https://github.com/fengxueguiren/CoPEFT)] ![](https://img.shields.io/github/stars/fengxueguiren/CoPEFT) 36 | 14. Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels (*CVPR'25*) [[`pdf`](https://arxiv.org/abs/2503.08421)] [[`code`](https://github.com/xmuqimingxia/DOtA)] ![](https://img.shields.io/github/stars/xmuqimingxia/DOtA) 37 | 15. V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detection (*CVPR'25*) [[`pdf`](https://arxiv.org/abs/2411.08402)] [[`code`](https://github.com/ylwhxht/V2X-R)] ![](https://img.shields.io/github/stars/ylwhxht/V2X-R) 38 | 16. End-to-End Autonomous Driving through V2X Cooperation (*AAAI'25*) [[`pdf`](https://arxiv.org/abs/2404.00717)] [[`code`](https://github.com/AIR-THU/UniV2X)] ![](https://img.shields.io/github/stars/AIR-THU/UniV2X) 39 | 17. Learning 3D Perception from Others' Predictions (*ICLR'25*) [[`pdf`](https://openreview.net/forum?id=Ylk98vWQuQ)] [[`code`](https://github.com/jinsuyoo/rnb-pop)] ![](https://img.shields.io/github/stars/jinsuyoo/rnb-pop) 40 | 18. CUDA-X: Unsupervised Domain-Adaptive Vehicle-to-Everything Collaboration via Knowledge Transfer and Alignment (*TNNLS'25*) [[`pdf`](https://ieeexplore.ieee.org/document/10891961)] 41 | 19. RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions (*CVPR'25*) [[`pdf`](https://openaccess.thecvf.com/content/CVPR2025/papers/Du_RCP-Bench_Benchmarking_Robustness_for_Collaborative_Perception_Under_Diverse_Corruptions_CVPR_2025_paper.pdf)] [[`code`](https://github.com/LuckyDush/RCP-Bench)] ![](https://img.shields.io/github/stars/LuckyDush/RCP-Bench) 42 | -------------------------------------------------------------------------------- /real_world_methods.md: -------------------------------------------------------------------------------- 1 | # A summary of state-of-the-art collaborative perception methods for real-world issues 2 | 3 |
4 |

5 | Table | 6 | Refer 7 |

8 |
9 | 10 | ## Table 11 | | Method | Venue | Modality | Scheme | Loc Error | Comm Issue | Discrep | Security | Code | 12 | |:----------------------:|:---------------:|:----------------:|:--------------------:|:---------------------:|:--------------------:|:-------------------:|:---------------------:|:-------------------------------------------------------------------------------:| 13 | | RobustV2VNet [1] | CoRL'20 | LiDAR | I | Loc, Pos | - | - | - | - | 14 | | AOMAC [2] | ICCV'21 | LiDAR | I | - | - | - | Attack | - | 15 | | P-CNN [3] | IoT'21 | Camera | E | - | - | - | Privacy | - | 16 | | FPV-RCNN [4] | RAL'22 | LiDAR | I | Loc, Pos | - | - | - | [Linkn](https://github.com/YuanYunshuang/FPV_RCNN) | 17 | | TCLF [5] | CVPR'22 | LiDAR | L | - | Laten | - | - | [Linkv](https://github.com/AIR-THU/DAIR-V2X) | 18 | | V2X-ViT [6] | ECCV'22 | LiDAR | I | Loc, Pos | Laten | - | - | [Linko](https://github.com/DerrickXuNu/v2x-vit) | 19 | | SyncNet [7] | ECCV'22 | LiDAR | I | - | Laten | - | - | [Linkc](https://github.com/MediaBrain-SJTU/SyncNet) | 20 | | TaskAgnostic [8] | CoRL'22 | LiDAR | I | - | - | Task | - | [Linkc](https://github.com/coperception/star) | 21 | | SecPCV [9] | TITS'22 | LiDAR | E | - | - | - | Privacy | - | 22 | | ModelAgnostic [10] | ICRA'23 | LiDAR | L | - | - | Model | - | [Linko](https://github.com/DerrickXuNu/model_anostic) | 23 | | MPDA [11] | ICRA'23 | LiDAR | I | - | - | Model | - | [Linko](https://github.com/DerrickXuNu/MPDA) | 24 | | CoAlign [12] | ICRA'23 | LiDAR | I, L | Loc, Pos | - | - | - | [Linko](https://github.com/yifanlu0227/CoAlign) | 25 | | LCRN [13] | TIV'23 | LiDAR | L | - | Loss | - | - | - | 26 | | OptiMatch [14] | IV'23 | LiDAR | L | Loc, Pos | - | - | - | - | 27 | | P2OD [15] | IoT'23 | Camera | E | - | - | - | Privacy | - | 28 | | ROBOSAC [16] | ICCV'23 | LiDAR | I | - | - | - | Attack | [Linkc](https://github.com/coperception/ROBOSAC) | 29 | | FFNet [17] | NeurIPS'23 | LiDAR | I | - | Laten | - | - | [Linkv](https://github.com/haibao-yu/FFNet-VIC3D) | 30 | | CoBEVFlow [18] | NeurIPS'23 | LiDAR | I | - | Laten | - | - | [Linko](https://github.com/MediaBrain-SJTU/CoBEVFlow) | 31 | | How2comm [19] | NeurIPS'23 | LiDAR | I | - | Laten | - | - | [Linko](https://github.com/ydk122024/How2comm) | 32 | | FeaCo [20] | MM'23 | LiDAR | I | Loc, Pos | - | - | - | [Linko](https://github.com/jmgu0212/FeaCo) | 33 | | ERMVP [21] | CVPR'24 | LiDAR | I | Loc, Pos | - | - | - | [Linko](https://github.com/Terry9a/ERMVP) | 34 | | MRCNet [22] | CVPR'24 | LiDAR | I | Loc, Pos | - | - | - | [Linko](https://github.com/IndigoChildren/collaborative-perception-MRCNet) | 35 | | RoCo [23] | MM'24 | LiDAR | I | Loc, Pos | - | - | - | [Linko](https://github.com/HuangZhe885/RoCo) | 36 | | PnPDA [24] | ECCV'24 | LiDAR | I | - | - | Model | - | [Linko](https://github.com/luotianyou349/PnPDA) | 37 | | Hetecooper [25] | ECCV'24 | LiDAR | I | - | - | Model | - | | 38 | | NEAT [26] | ECCV'24 | LiDAR | I | Loc, Pos | Laten | - | - | | 39 | | V2X-INCOP [27] | TIV'24 | LiDAR | I | - | Inter | - | - | - | 40 | | MADE [28] | IROS'24 | LiDAR | I | - | - | - | Attack | - | 41 | | CP-Guard [29] | AAAI'25 | LiDAR | I | - | - | - | Attack | [Linkc](https://github.com/CP-Security/CP-Guard) | 42 | | PLDA [30] | AAAI'25 | LiDAR | I | - | - | Model | - | - | 43 | | BEVSync [31] | AAAI'25 | LiDAR | I | - | Laten | - | - | - | 44 | | STAMP [32] | ICLR'25 | LiDAR, Camera | I | - | - | Model, Task | - | [Linko](https://github.com/taco-group/STAMP) | 45 | | PolyInter [33] | CVPR'25 | LiDAR | I | - | - | Model | - | - | 46 | 47 | 48 | Notes: 49 | - Schemes include early (E), intermediate (I) and late (L) collaboration. 50 | - **Loc Error** includes localization (**Loc**) and pose (**Pos**) errors. 51 | - **Comm Issue** includes latency (**Laten**), interruption (**Inter**) and loss (**Loss**). 52 | - **Discrep** includes model (**Model**) and task (**Task**) discrepancies. 53 | - **Security** includes attack defense (**Attack**) and privacy protection (**Privacy**). 54 | - **Code Framework**: o ([OpenCOOD](https://github.com/DerrickXuNu/OpenCOOD)), v ([VIC3D](https://github.com/AIR-THU/DAIR-V2X)), c ([CoPerception](https://github.com/coperception/coperception)), n (Non-mainstream framework) 55 | 56 | Back to [Contents](README.md) 🔙 57 | 58 | ## References 59 | ### Published 60 | 1. Learning to Communicate and Correct Pose Errors (CoRL'20) [[`pdf`](https://arxiv.org/abs/2011.05289)] 61 | 2. Adversarial attacks on multi-agent communication (ICCV'21) [[`pdf`](https://arxiv.org/abs/2101.06560)] 62 | 3. Toward lightweight, privacy-preserving cooperative object classification for connected autonomous vehicles (IoT'21) [[`pdf`](https://ieeexplore.ieee.org/document/9468670)] 63 | 4. Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving (RAL'22) [[`pdf`](https://arxiv.org/abs/2109.11615)] [[`code`](https://github.com/YuanYunshuang/FPV_RCNN)] 64 | 5. DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection (CVPR'22) [[`pdf`](https://arxiv.org/abs/2204.05575)] [[`code`](https://github.com/AIR-THU/DAIR-V2X)] 65 | 6. V2X-ViT: Vehicle-to-everything cooperative perception with vision transformer (ECCV'22) [[`pdf`](https://arxiv.org/abs/2203.10638)] [[`code`](https://github.com/DerrickXuNu/v2x-vit)] 66 | 7. Latency-Aware Collaborative Perception (ECCV'22) [[`pdf`](https://arxiv.org/abs/2207.08560)] [[`code`](https://github.com/MediaBrain-SJTU/SyncNet)] 67 | 8. Multi-robot scene completion: Towards task-agnostic collaborative perception (CoRL'22) [[`pdf`](https://openreview.net/forum?id=hW0tcXOJas2)] [[`code`](https://github.com/coperception/star)] 68 | 9. Edge-Cooperative Privacy-Preserving Object Detection Over Random Point Cloud Shares for Connected Autonomous Vehicles (TITS'22) [[`pdf`](https://ieeexplore.ieee.org/document/9928424)] 69 | 10. Model-Agnostic Multi-Agent Perception Framework (ICRA'23) [[`pdf`](https://arxiv.org/abs/2203.13168)] [[`code`](https://github.com/DerrickXuNu/model_anostic)] 70 | 11. Bridging the Domain Gap for Multi-Agent Perception (ICRA'23) [[`pdf`](https://arxiv.org/abs/2210.08451)] [[`code`](https://github.com/DerrickXuNu/MPDA)] 71 | 12. Robust Collaborative 3D Object Detection in Presence of Pose Errors (ICRA'23) [[`pdf`](https://arxiv.org/abs/2211.07214)] [[`code`](https://github.com/yifanlu0227/CoAlign)] 72 | 13. Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communication (TIV'23) [[`pdf`](https://arxiv.org/abs/2212.08273)] 73 | 14. A Cooperative Perception System Robust to Localization Errors (IV'23) [[`pdf`](https://arxiv.org/abs/2210.06289)] 74 | 15. Achieving Lightweight and Privacy-Preserving Object Detection for Connected Autonomous Vehicles (IoT'23) [[`pdf`](https://ieeexplore.ieee.org/document/9913215)] 75 | 16. Among Us: Adversarially Robust Collaborative Perception by Consensus (ICCV'23) [[`pdf`](https://arxiv.org/abs/2303.09495)] [[`code`](https://github.com/coperception/ROBOSAC)] 76 | 17. Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection (NeurIPS'23) [[`pdf`](https://openreview.net/forum?id=gsglrhvQxX)] [[`code`](https://github.com/haibao-yu/FFNet-VIC3D)] 77 | 18. Robust Asynchronous Collaborative 3D Detection via Bird’s Eye View Flow (NeurIPS'23) [[`pdf`](https://arxiv.org/abs/2309.16940)] [[`code`](https://github.com/MediaBrain-SJTU/CoBEVFlow)] 78 | 19. How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception (NeurIPS'23) [[`pdf`](https://openreview.net/forum?id=Dbaxm9ujq6)] [[`code`](https://github.com/ydk122024/How2comm)] 79 | 20. FeaCo: Reaching Robust Feature-Level Consensus in Noisy Pose Conditions (MM'23) [[`pdf`](https://dl.acm.org/doi/abs/10.1145/3581783.3611880)] 80 | 21. ERMVP: Communication-Efficient and Collaboration-Robust Multi-Vehicle Perception in Challenging Environments (CVPR'24) [[`pdf`](https://openaccess.thecvf.com/content/CVPR2024/papers/Zhang_ERMVP_Communication-Efficient_and_Collaboration-Robust_Multi-Vehicle_Perception_in_Challenging_Environments_CVPR_2024_paper.pdf)] 81 | 22. Multi-agent Collaborative Perception via Motion-aware Robust Communication Network (CVPR'24) [[`pdf`](https://openaccess.thecvf.com/content/CVPR2024/papers/Hong_Multi-agent_Collaborative_Perception_via_Motion-aware_Robust_Communication_Network_CVPR_2024_paper.pdf)] 82 | 23. RoCo: Robust Cooperative Perception By Iterative Object Matching and Pose Adjustment (MM'24) [[`pdf`](https://openreview.net/forum?id=TFFnsgu2Pr)] 83 | 24. Plug and Play: A Representation Enhanced Domain Adapter for Collaborative Perception (ECCV'24) [[`pdf`](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/10564.pdf)] [[`code`](https://github.com/luotianyou349/PnPDA)] 84 | 25. Hetecooper: Feature Collaboration Graph for Heterogeneous Collaborative Perception (ECCV'24) [[`pdf`](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/07071.pdf)] 85 | 26. Align before Collaborate: Mitigating Feature Misalignment for Robust Multi-Agent Perception (ECCV'24) [[`pdf`](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/00560.pdf)] 86 | 27. Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Driving (TIV'24) [[`pdf`](https://arxiv.org/abs/2304.11821)] 87 | 28. Malicious Agent Detection for Robust Multi-Agent Collaborative Perception (IROS'24) [[`pdf`](https://arxiv.org/abs/2304.11821)] 88 | 29. CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird’s Eye View Perception (AAAI'25) [[`pdf`](https://arxiv.org/abs/2412.12000)] [[`code`](https://github.com/CP-Security/CP-Guard)] 89 | 30. Privacy-Preserving V2X Collaborative Perception Integrating Unknown Collaborators (AAAI'25) [[`pdf`](https://ojs.aaai.org/index.php/AAAI/article/view/32619)] 90 | 31. BEVSync: Asynchronous Data Alignment for Camera-based Vehicle-Infrastructure Cooperative Perception Under Uncertain Delays (AAAI'25) [[`pdf`](https://ojs.aaai.org/index.php/AAAI/article/view/33611)] 91 | 32. STAMP: Scalable Task And Model-agnostic Collaborative Perception (ICLR'25) [[`pdf`](https://arxiv.org/abs/2501.18616)] [[`code`](https://github.com/taco-group/STAMP)] 92 | 33. One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception (CVPR'25) [[`pdf`](https://arxiv.org/abs/2411.16799)] 93 | 94 | --------------------------------------------------------------------------------