pith. sign in

arxiv: 2606.00416 · v1 · pith:4M2CW6EJnew · submitted 2026-05-29 · 💻 cs.CV

4D Radar Meets LiDAR and Camera: Cooperative Perception under Adverse Weather

Melih Yazgan , Iramm Hamdard , Qiyuan Wu , J.Marius Zoellner This is my paper

Pith reviewed 2026-06-28 22:27 UTC · model grok-4.3

classification 💻 cs.CV
keywords cooperative perception4D imaging radaradverse weathersensor fusionautonomous drivingLiDAR degradationmulti-agent systems
0
0 comments X

The pith

4D imaging radar integrated into cooperative perception maintains performance when LiDAR and cameras degrade in fog and rain.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows that 4D imaging radar can be fused with existing camera and LiDAR pipelines to deliver robust multi-agent perception under adverse weather. It introduces a Doppler-guided spatial attention mechanism that enables radar to either replace or complement degraded sensors across two representative backbones. New benchmarks called OPV2V-R and Adver-City-R apply physics-based LiDAR degradation to support evaluation, with additional tests on real MAN TruckScenes data. If the approach works as claimed, vehicles could continue reliable cooperative detection even when traditional sensors fail. The results position radar as a key modality for all-weather collaborative autonomy.

Core claim

By extending radar-camera and LiDAR-radar pipelines with a Doppler-guided spatial attention mechanism for multi-agent fusion, 4D imaging radar delivers substantial robustness gains in fog and rain, including large improvements when it substitutes for degraded LiDAR, as validated on the released OPV2V-R and Adver-City-R benchmarks and on MAN TruckScenes.

What carries the argument

Doppler-guided spatial attention mechanism that performs multi-agent fusion by leveraging radar velocity information to weight spatial features across agents.

If this is right

  • Radar-camera pipelines can maintain accuracy when LiDAR is fully unavailable due to weather.
  • LiDAR-radar pipelines gain complementary coverage that offsets camera and LiDAR losses.
  • The same fusion architecture transfers from simulation to recorded truck data.
  • Collaborative perception no longer requires every agent to have perfectly functioning optical sensors.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Benchmark releases with controlled degradation could become standard for testing other weather-robust modalities.
  • The Doppler attention idea might extend to single-agent fusion or to other velocity-capable sensors.
  • Longer-term, fleets could reduce reliance on multiple high-cost LiDAR units if radar proves sufficient in mixed conditions.

Load-bearing premise

The physics-based LiDAR degradation model used to create the OPV2V-R and Adver-City-R benchmarks accurately captures how real LiDAR behaves in fog and rain.

What would settle it

Field tests in genuine fog or rain where replacing simulated-degraded LiDAR with real 4D radar produces no measurable detection improvement over the non-radar baseline.

Figures

Figures reproduced from arXiv: 2606.00416 by Iramm Hamdard, J.Marius Zoellner, Melih Yazgan, Qiyuan Wu.

Figure 1
Figure 1. Figure 1: Impact of adverse weather on LiDAR and radar per [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the proposed architecture, illustrated on BM2CP where radar replaces LiDAR. Radar features are encoded via a [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Comparison of point clouds before augmentation (top [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Overview of Doppler-aware motion encoding. Radar [PITH_FULL_IMAGE:figures/full_fig_p004_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Overview of Doppler Mask Generation and Mask-Guided Spatial Attention. The Point-Level Dynamic Map illustrates how [PITH_FULL_IMAGE:figures/full_fig_p005_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Robustness analysis on Adver-City-R (Combined Fog [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
read the original abstract

Cooperative perception is important for autonomous driving but remains fragile when cameras and LiDAR degrade in adverse weather. We address this challenge by integrating 4D imaging radar as a weather-robust modality into collaborative perception and introducing a Doppler-guided spatial attention mechanism for multi-agent fusion. Our approach extends two representative backbones: a radar-camera pipeline where radar substitutes LiDAR, and a LiDAR-radar pipeline where radar complements LiDAR. To support evaluation, we release radar-augmented benchmarks, OPV2V-R and Adver-City-R, with physics-based LiDAR degradation. Experiments show strong robustness gains in fog and rain, including substantial improvements when radar replaces degraded LiDAR. Additional validation on MAN TruckScenes demonstrates transfer beyond simulation. Overall, our results highlight 4D imaging radar as a robust modality for all-weather collaborative perception. Dataset and code are available at: https://url.fzi.de/SlimComm.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The paper claims that integrating 4D imaging radar into cooperative perception systems, via a Doppler-guided spatial attention mechanism for multi-agent fusion, yields strong robustness gains under fog and rain. It extends two backbones (radar-camera substitution and LiDAR-radar complement), releases physics-based LiDAR-degraded benchmarks OPV2V-R and Adver-City-R, reports experimental improvements on these benchmarks (including radar replacing degraded LiDAR), and shows transfer on real MAN TruckScenes data.

Significance. If the central claims hold, the work positions 4D imaging radar as a practical weather-robust modality for collaborative perception, directly addressing fragility of camera/LiDAR fusion in adverse conditions. The benchmark releases and code availability would support follow-on research.

major comments (1)
  1. [Abstract; benchmark release paragraph] Abstract and benchmark construction section: the headline robustness gains (including radar replacing degraded LiDAR) are demonstrated exclusively on OPV2V-R and Adver-City-R, which rely on an unvalidated physics-based LiDAR degradation model. No quantitative comparison of simulated point density, noise distribution, or intensity statistics against real adverse-weather LiDAR is provided, and the MAN TruckScenes experiment does not isolate or validate this model. This is load-bearing for the central empirical claim.
minor comments (1)
  1. [Abstract] The abstract reports only qualitative gains without any numerical values, error bars, or ablation summaries, which reduces immediate readability even though full results appear later.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback. We address the single major comment below and outline the planned revisions.

read point-by-point responses

  1. Referee: [Abstract; benchmark release paragraph] Abstract and benchmark construction section: the headline robustness gains (including radar replacing degraded LiDAR) are demonstrated exclusively on OPV2V-R and Adver-City-R, which rely on an unvalidated physics-based LiDAR degradation model. No quantitative comparison of simulated point density, noise distribution, or intensity statistics against real adverse-weather LiDAR is provided, and the MAN TruckScenes experiment does not isolate or validate this model. This is load-bearing for the central empirical claim.

    Authors: We agree that the manuscript does not contain a direct quantitative comparison (e.g., point-density histograms, noise statistics, or intensity distributions) between the physics-based degradation model and real adverse-weather LiDAR captures. The model follows established physical scattering principles previously used in the LiDAR simulation literature, but we did not perform or report such a side-by-side validation. The MAN TruckScenes experiment demonstrates transfer of the overall method to real adverse-weather data; however, it does not isolate or validate the specific degradation parameters used in the simulated benchmarks. We will revise the benchmark-construction section to provide additional implementation details of the degradation model and add an explicit limitations paragraph stating that the reported gains on OPV2V-R and Adver-City-R rest on simulation and that direct real-world statistical validation of the degradation model remains future work. This revision will be made in the next version of the manuscript. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical results on released benchmarks with no derivation chain or fitted predictions.

full rationale

The paper reports experimental robustness gains on OPV2V-R and Adver-City-R benchmarks generated via a physics-based LiDAR degradation model, plus transfer on MAN TruckScenes. No equations, parameter fits, or predictions are described that reduce to inputs by construction. No self-citation load-bearing steps, uniqueness theorems, or ansatzes appear in the provided text. The central claims are direct empirical measurements on the introduced datasets and are therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Based solely on the abstract; no explicit free parameters, axioms, or invented physical entities are stated. Standard deep-learning training assumptions are implicit but not detailed.

pith-pipeline@v0.9.1-grok · 5700 in / 1068 out tokens · 20731 ms · 2026-06-28T22:27:12.557657+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

48 extracted references · 1 canonical work pages

  1. [1]

    Lang, Sourabh V ora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yuning Pan, Giancarlo Baldan, and Oscar Beijbom

    Holger Caesar, Varun Bankiti, Alex H. Lang, Sourabh V ora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yuning Pan, Giancarlo Baldan, and Oscar Beijbom. nuscenes: A mul- timodal dataset for autonomous driving. InProceedings of 8 the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 11618–11628, 2020. 2

    2020

  2. [2]

    CARLA: An open urban driving simulator

    Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. CARLA: An open urban driving simulator. InProceedings of the 1st Annual Conference on Robot Learning, pages 1–16, 2017. 1, 5

    2017

  3. [3]

    Man truckscenes: A multimodal dataset for autonomous trucking in diverse conditions, 2024

    Felix Fent, Fabian Kuttenreich, Florian Ruch, Farija Rizwin, Stefan Juergens, Lorenz Lechermann, Christian Nissler, An- drea Perl, Ulrich V oll, Min Yan, and Markus Lienkamp. Man truckscenes: A multimodal dataset for autonomous trucking in diverse conditions, 2024. 2, 5, 8

    2024

  4. [4]

    Ramp-cnn: A novel neural network for enhanced automo- tive radar object recognition.IEEE Sensors Journal, 21(4): 5119–5132, 2021

    Xiangyu Gao, Guanbin Xing, Sumit Roy, and Hui Liu. Ramp-cnn: A novel neural network for enhanced automo- tive radar object recognition.IEEE Sensors Journal, 21(4): 5119–5132, 2021. 2

    2021

  5. [5]

    Doppdrive: Doppler-driven temporal aggregation for improved radar object detection

    Yuval Haitman and Oded Bialer. Doppdrive: Doppler-driven temporal aggregation for improved radar object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 26085–26094, 2025. 8

    2025

  6. [6]

    Simple-bev: What really mat- ters for multi-sensor bev perception? In2023 IEEE Inter- national Conference on Robotics and Automation (ICRA), pages 2759–2765

    Adam W Harley, Zhaoyuan Fang, Jie Li, Rares Ambrus, and Katerina Fragkiadaki. Simple-bev: What really mat- ters for multi-sensor bev perception? In2023 IEEE Inter- national Conference on Robotics and Automation (ICRA), pages 2759–2765. IEEE, 2023. 1

    2023

  7. [7]

    Where2comm: Communication-efficient collab- orative perception via spatial confidence maps.Advances in neural information processing systems, 35:4874–4886,

    Yue Hu, Shaoheng Fang, Zixing Lei, Yiqi Zhong, and Si- heng Chen. Where2comm: Communication-efficient collab- orative perception via spatial confidence maps.Advances in neural information processing systems, 35:4874–4886,

  8. [8]

    Nguyen, Mostafa Rahimi Azghadi, Yuxuan Xia, Qing-Long Han, and Sumei Sun

    Tao Huang, Jianan Liu, Xi Zhou, Dinh C. Nguyen, Mostafa Rahimi Azghadi, Yuxuan Xia, Qing-Long Han, and Sumei Sun. V2x cooperative perception for autonomous driving: Recent advances and challenges, 2024. 1

    2024

  9. [9]

    V2x-r: Cooperative lidar-4d radar fusion with denoising dif- fusion for 3d object detection

    Xun Huang, Jinlong Wang, Qiming Xia, Siheng Chen, Bisheng Yang, Xin Li, Cheng Wang, and Chenglu Wen. V2x-r: Cooperative lidar-4d radar fusion with denoising dif- fusion for 3d object detection. In2025 IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR), pages 27390–27400, 2025. 1, 2, 6, 7

    2025

  10. [10]

    Weather- aware collaborative perception with uncertainty reduction

    Ping Jiang, Xiaoheng Deng, Weishang Wu, Lixin Lin, Xuechen Chen, Chen Chen, and Shaohua Wan. Weather- aware collaborative perception with uncertainty reduction. IEEE Transactions on Intelligent Transportation Systems, 25 (12):20059–20072, 2024. 2

    2024

  11. [11]

    Adver-city: Open-source multi-modal dataset for collaborative perception under ad- verse weather conditions, 2025

    Mateus Karvat and Sidney Givigi. Adver-city: Open-source multi-modal dataset for collaborative perception under ad- verse weather conditions, 2025. 1, 2, 5

    2025

  12. [12]

    Lidar light scattering augmentation (lisa): Physics-based simulation of adverse weather conditions for 3d object detection.arXiv preprint arXiv:2107.07004, 2021

    Velat Kilic, Deepti Hegde, Vishwanath Sindagi, A Brinton Cooper, Mark A Foster, and Vishal M Patel. Lidar light scattering augmentation (lisa): Physics-based simulation of adverse weather conditions for 3d object detection.arXiv preprint arXiv:2107.07004, 2021. 1, 5

    work page arXiv 2021

  13. [13]

    Craft: Camera-radar 3d object detection with spatio-contextual fusion transformer

    Youngseok Kim, Sanmin Kim, Jun Won Choi, and Dong- suk Kum. Craft: Camera-radar 3d object detection with spatio-contextual fusion transformer. InProceedings of the AAAI Conference on Artificial Intelligence, pages 1160– 1168, 2023. 2

    2023

  14. [14]

    Lang, Sourabh V ora, Holger Caesar, Lubing Zhou, Jiong Yang, and Oscar Beijbom

    Alex H. Lang, Sourabh V ora, Holger Caesar, Lubing Zhou, Jiong Yang, and Oscar Beijbom. Pointpillars: Fast encoders for object detection from point clouds. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. 8

    2019

  15. [15]

    V2x-dgw: Domain generalization for multi-agent perception under ad- verse weather conditions, 2025

    Baolu Li, Jinlong Li, Xinyu Liu, Runsheng Xu, Zhengzhong Tu, Jiacheng Guo, Xiaopeng Li, and Hongkai Yu. V2x-dgw: Domain generalization for multi-agent perception under ad- verse weather conditions, 2025. 2

    2025

  16. [16]

    Autonomous vehicles: A critical review (2004-2024) and a vision for the future.Authorea Preprints, 2025

    Henry Liu, Zhong Cao, Xintao Yan, Shuo Feng, and Qiujing Lu. Autonomous vehicles: A critical review (2004-2024) and a vision for the future.Authorea Preprints, 2025. 1

    2004

  17. [17]

    Hongsi Liu, Jun Liu, Guangfeng Jiang, and Xin Jin. Mssf: A 4d radar and camera fusion framework with multi-stage sam- pling for 3d object detection in autonomous driving.IEEE Transactions on Intelligent Transportation Systems, 26(6): 8641–8656, 2025. 2

    2025

  18. [18]

    A survey on autonomous driving datasets: Statistics, annotation quality, and a future outlook.IEEE Transactions on Intelligent Vehicles, 2024

    Mingyu Liu, Ekim Yurtsever, Jonathan Fossaert, Xingcheng Zhou, Walter Zimmer, Yuning Cui, Bare Luka Zagar, and Alois C Knoll. A survey on autonomous driving datasets: Statistics, annotation quality, and a future outlook.IEEE Transactions on Intelligent Vehicles, 2024. 1

    2024

  19. [19]

    Radarpillars: Efficient object detec- tion from 4d radar point clouds

    Alexander Musiat, Laurenz Reichardt, Michael Schulze, and Oliver Wasenm¨uller. Radarpillars: Efficient object detec- tion from 4d radar point clouds. In2024 IEEE 27th Inter- national Conference on Intelligent Transportation Systems (ITSC), pages 1656–1663, 2024. 2, 3

    2024

  20. [20]

    Centerfusion: Center-based radar and camera fusion for 3d object detection

    Ramin Nabati and Hairong Qi. Centerfusion: Center-based radar and camera fusion for 3d object detection. InProceed- ings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 1527–1536, 2021. 2

    2021

  21. [21]

    A deep learning-based radar and camera sensor fusion architecture for object detec- tion

    Felix Nobis, Maximilian Geisslinger, Markus Weber, Jo- hannes Betz, and Markus Lienkamp. A deep learning-based radar and camera sensor fusion architecture for object detec- tion. In2019 Symposium on Sensor Data Fusion: Trends, Solutions, Applications (SDF), pages 1–7, 2019. 2

    2019

  22. [22]

    K-radar: 4d radar object detection for autonomous driving in various weather conditions.Advances in Neural Information Processing Systems, 35:3819–3829, 2022

    Dong-Hee Paek, Seung-Hyun Kong, and Kevin Tirta Wijaya. K-radar: 4d radar object detection for autonomous driving in various weather conditions.Advances in Neural Information Processing Systems, 35:3819–3829, 2022. 2

    2022

  23. [23]

    Andras Palffy, Ewoud Pool, Srimannarayana Baratam, Ju- lian F. P. Kooij, and Dariu M. Gavrila. Multi-class road user detection with 3+1d radar in the view-of-delft dataset.IEEE Robotics and Automation Letters, 7(2):4961–4968, 2022. 6

    2022

  24. [24]

    4d mmwave radar for sensing enhancement in adverse environments: Advances and challenges, 2025

    Xiangyuan Peng, Miao Tang, Huawei Sun, Kay Bierzyn- ski, Lorenzo Servadei, and Robert Wille. 4d mmwave radar for sensing enhancement in adverse environments: Advances and challenges, 2025. 1

    2025

  25. [25]

    Adaptive feature fu- sion for cooperative perception using lidar point clouds

    Donghao Qiao and Farhana Zulkernine. Adaptive feature fu- sion for cooperative perception using lidar point clouds. In Proceedings of the IEEE/CVF winter conference on applica- tions of computer vision, pages 1186–1195, 2023. 2, 6

    2023

  26. [26]

    Scalability in perception for au- tonomous driving: Waymo open dataset, 2020

    Pei Sun, Henrik Kretzschmar, Xerxes Dotiwalla, Aurelien Chouard, Vijaysai Patnaik, Paul Tsui, James Guo, Yin Zhou, Yuning Chai, Benjamin Caine, Vijay Vasudevan, Wei Han, Jiquan Ngiam, Hang Zhao, Aleksei Timofeev, Scott Ettinger, Maxim Krivokon, Amy Gao, Aditya Joshi, Sheng Zhao, 9 Shuyang Cheng, Yu Zhang, Jonathon Shlens, Zhifeng Chen, and Dragomir Anguel...

    2020

  27. [27]

    Simulating realistic rain, snow, and fog varia- tions for comprehensive performance characterization of li- dar perception

    Sven Teufel, Georg V olk, Alexander V on Bernuth, and Oliver Bringmann. Simulating realistic rain, snow, and fog varia- tions for comprehensive performance characterization of li- dar perception. In2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring), pages 1–7, 2022. 2

    2022

  28. [28]

    Per- ception for connected autonomous vehicles under adverse weather conditions

    Dimitra Tsakmakopoulou and Konstantinos Moustakas. Per- ception for connected autonomous vehicles under adverse weather conditions. In2024 IEEE/RSJ International Confer- ence on Intelligent Robots and Systems (IROS), pages 3161– 3166, 2024. 2

    2024

  29. [29]

    Perception methods for adverse weather based on vehicle infrastructure cooperation system: A re- view.Sensors, 24(2), 2024

    Jizhao Wang, Zhizhou Wu, Yunyi Liang, Jinjun Tang, and Huimiao Chen. Perception methods for adverse weather based on vehicle infrastructure cooperation system: A re- view.Sensors, 24(2), 2024. 2

    2024

  30. [30]

    Interfusion: Interaction-based 4d radar and lidar fusion for 3d object detection

    Li Wang, Xinyu Zhang, Baowei Xv, Jinzhao Zhang, Rong Fu, Xiaoyu Wang, Lei Zhu, Haibing Ren, Pingping Lu, Jun Li, and Huaping Liu. Interfusion: Interaction-based 4d radar and lidar fusion for 3d object detection. In2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 12247–12253, 2022. 2

    2022

  31. [31]

    Collaborative perception datasets for autonomous driv- ing: A review.IEEE Sensors Journal, 2025

    Naibang Wang, Deyong Shang, Yan Gong, Xiaoxi Hu, Ziy- ing Song, Lei Yang, Yuhan Huang, Xiaoyu Wang, and Jianli Lu. Collaborative perception datasets for autonomous driv- ing: A review.IEEE Sensors Journal, 2025. 2

    2025

  32. [32]

    Multi-sensor fusion in automated driving: A survey.IEEE Access, 8: 2847–2868, 2020

    Zhangjing Wang, Yu Wu, and Qingqing Niu. Multi-sensor fusion in automated driving: A survey.IEEE Access, 8: 2847–2868, 2020. 1

    2020

  33. [33]

    Foundation models for au- tonomous driving systems: An initial roadmap.ACM Trans- actions on Software Engineering and Methodology, 2026

    Xiongfei Wu, Mingfei Cheng, Xiaoning Ren, Qiang Hu, Jianlang Chen, Yuheng Huang, Maxime Cordy, Yao Zhang, Xiaofei Xie, Lei Ma, et al. Foundation models for au- tonomous driving systems: An initial roadmap.ACM Trans- actions on Software Engineering and Methodology, 2026. 1

    2026

  34. [34]

    Lxl: Lidar excluded lean 3d object detection with 4d imaging radar and camera fusion.IEEE Transactions on Intelligent Vehicles, 9(1):79–92, 2024

    Weiyi Xiong, Jianan Liu, Tao Huang, Qing-Long Han, Yux- uan Xia, and Bing Zhu. Lxl: Lidar excluded lean 3d object detection with 4d imaging radar and camera fusion.IEEE Transactions on Intelligent Vehicles, 9(1):79–92, 2024. 2

    2024

  35. [35]

    Opv2v: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communica- tion

    Runsheng Xu, Hao Xiang, Xin Xia, Xu Han, Jinlong Li, and Jiaqi Ma. Opv2v: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communica- tion. In2022 International Conference on Robotics and Au- tomation (ICRA), pages 2583–2589. IEEE, 2022. 1, 2, 6

    2022

  36. [36]

    Radarnet: Exploiting radar for robust per- ception of dynamic objects

    Bin Yang, Runsheng Guo, Ming Liang, Sergio Casas, and Raquel Urtasun. Radarnet: Exploiting radar for robust per- ception of dynamic objects. InEuropean conference on com- puter vision, pages 496–512. Springer, 2020. 3

    2020

  37. [37]

    A review of envi- ronmental perception technology based on multi-sensor in- formation fusion in autonomous driving.World Electric Ve- hicle Journal, 16(1), 2025

    Boquan Yang, Jixiong Li, and Ting Zeng. A review of envi- ronmental perception technology based on multi-sensor in- formation fusion in autonomous driving.World Electric Ve- hicle Journal, 16(1), 2025. 1

    2025

  38. [38]

    Spatio-temporal domain awareness for multi-agent collab- orative perception

    Kun Yang, Dingkang Yang, Jingyu Zhang, Mingcheng Li, Yang Liu, Jing Liu, Hanqi Wang, Peng Sun, and Liang Song. Spatio-temporal domain awareness for multi-agent collab- orative perception. InProceedings of the IEEE/CVF In- ternational Conference on Computer Vision (ICCV), pages 23383–23392, 2023. 6

    2023

  39. [39]

    V2x-radar: A multi-modal dataset with 4d radar for cooperative perception.Advances in Neural In- formation Processing Systems (NeurIPS), 2025

    Lei Yang, Xinyu Zhang, Jun Li, Chen Wang, Jiaqi Ma, Zhiy- ing Song, Tong Zhao, Ziying Song, Li Wang, Mo Zhou, Yang Shen, and Chen Lv. V2x-radar: A multi-modal dataset with 4d radar for cooperative perception.Advances in Neural In- formation Processing Systems (NeurIPS), 2025. 2

    2025

  40. [40]

    Radar-camera fusion for object detection and semantic segmentation in au- tonomous driving: A comprehensive review.IEEE Transac- tions on Intelligent Vehicles, 9(1):2094–2128, 2024

    Shanliang Yao, Runwei Guan, Xiaoyu Huang, Zhuoxiao Li, Xiangyu Sha, Yong Yue, Eng Gee Lim, Hyungjoon Seo, Ka Lok Man, Xiaohui Zhu, and Yutao Yue. Radar-camera fusion for object detection and semantic segmentation in au- tonomous driving: A comprehensive review.IEEE Transac- tions on Intelligent Vehicles, 9(1):2094–2128, 2024. 1

    2094

  41. [41]

    Mar- ius Z¨ollner

    Melih Yazgan, Mythra Varun Akkanapragada, and J. Mar- ius Z¨ollner. Collaborative perception datasets in autonomous driving: A survey. In2024 IEEE Intelligent Vehicles Sympo- sium (IV), pages 2269–2276, 2024. 2

    2024

  42. [42]

    Real-world problems in collaborative per- ception: A categorized review of intermediate fusion meth- ods.IEEE IV, 2024

    Melih Yazgan, Thomas Graf, Min Liu, Tobias Fleck, and J Marius Z¨ollner. Real-world problems in collaborative per- ception: A categorized review of intermediate fusion meth- ods.IEEE IV, 2024. 1

    2024

  43. [43]

    Slimcomm: Doppler-guided sparse queries for bandwidth-efficient cooperative 3-d perception

    Melih Yazgan, Qiyuan Wu, Iramm Hamdard, Shiqi Li, and J Marius Zoellner. Slimcomm: Doppler-guided sparse queries for bandwidth-efficient cooperative 3-d perception. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 1782–1791, 2025. 2, 3, 6, 7

    2025

  44. [44]

    Dair-v2x: A large-scale dataset for vehicle- infrastructure cooperative 3d object detection

    Haibao Yu, Yizhen Luo, Mao Shu, Yiyi Huo, Zebang Yang, Yifeng Shi, Zhenglong Guo, Hanyu Li, Xing Hu, Jirui Yuan, and Zaiqing Nie. Dair-v2x: A large-scale dataset for vehicle- infrastructure cooperative 3d object detection. InProceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 21361–21370, 2022. 1, 2

    2022

  45. [45]

    Perception and sensing for autonomous ve- hicles under adverse weather conditions: A survey.ISPRS Journal of Photogrammetry and Remote Sensing, 196:146– 177, 2023

    Yuxiao Zhang, Alexander Carballo, Hanting Yang, and Kazuya Takeda. Perception and sensing for autonomous ve- hicles under adverse weather conditions: A survey.ISPRS Journal of Photogrammetry and Remote Sensing, 196:146– 177, 2023. 1, 2, 5

    2023

  46. [46]

    Bm2cp: Effi- cient collaborative perception with lidar-camera modalities

    Binyu Zhao, Wei ZHANG, and Zhaonian Zou. Bm2cp: Effi- cient collaborative perception with lidar-camera modalities. InConference on Robot Learning, pages 1022–1035. PMLR,

  47. [47]

    Rc- fusion: Fusing 4-d radar and camera with bird’s-eye view features for 3-d object detection.IEEE Transactions on In- strumentation and Measurement, 72:1–14, 2023

    Lianqing Zheng, Sen Li, Bin Tan, Long Yang, Sihan Chen, Libo Huang, Jie Bai, Xichan Zhu, and Zhixiong Ma. Rc- fusion: Fusing 4-d radar and camera with bird’s-eye view features for 3-d object detection.IEEE Transactions on In- strumentation and Measurement, 72:1–14, 2023. 2

    2023

  48. [48]

    Walter Zimmer, Gerhard Arya Wardana, Suren Sritharan, Xingcheng Zhou, Rui Song, and Alois C. Knoll. Tum- traf v2x cooperative perception dataset. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 22668–22677, 2024. 2 10

    2024