Foundation Models for V2X-Based Cooperative Autonomous Driving


CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning
Rui Gan,
Junyi Ma,
Pei Li,
Xingyou Yang,
Kai Cheng,
Sikai Chen,
Bin Ran
[pdf] [arXiv]
[bibtex]
@InProceedings{Gan_2026_CVPR, author = {Gan, Rui and Ma, Junyi and Li, Pei and Yang, Xingyou and Cheng, Kai and Chen, Sikai and Ran, Bin}, title = {CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {718-727} }

GaussianDet3D: Bridging Gaussian Splatting and Sparse LiDAR Detection for Multi-View 3D Object Detection
Malaz Tamim,
Wenzhao Zheng,
Johannes Michael Meier,
Daniel Cremers,
Kurt Keutzer
[pdf]
[bibtex]
@InProceedings{Tamim_2026_CVPR, author = {Tamim, Malaz and Zheng, Wenzhao and Meier, Johannes Michael and Cremers, Daniel and Keutzer, Kurt}, title = {GaussianDet3D: Bridging Gaussian Splatting and Sparse LiDAR Detection for Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {766-774} }

IAO-SLAM: Real-time Illumination-Aware Object SLAM for Robust Perception in Low-Light Environments
Pengju Zhen,
Huilin Yin,
Linchuan Zhang,
Xin Su
[pdf]
[bibtex]
@InProceedings{Zhen_2026_CVPR, author = {Zhen, Pengju and Yin, Huilin and Zhang, Linchuan and Su, Xin}, title = {IAO-SLAM: Real-time Illumination-Aware Object SLAM for Robust Perception in Low-Light Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {815-822} }

DinoRADE: Full Spectral Radar-Camera Fusion with Vision Foundation Model Features for Multi-class Object Detection in Adverse Weather
Christof Leitgeb,
Thomas Puchleitner,
Max Peter Ronecker,
Daniel Watzenig
[pdf] [arXiv]
[bibtex]
@InProceedings{Leitgeb_2026_CVPR, author = {Leitgeb, Christof and Puchleitner, Thomas and Ronecker, Max Peter and Watzenig, Daniel}, title = {DinoRADE: Full Spectral Radar-Camera Fusion with Vision Foundation Model Features for Multi-class Object Detection in Adverse Weather}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {737-746} }

V2X-UniPool: Unifying Multimodal Perception and Knowledge Reasoning for Autonomous Driving
Xuewen Luo,
Fengze Yang,
Ding Fan,
Xiangbo Gao,
Bo Yu,
Zihao Li,
Zhengzhong Tu,
Yang Zhou,
Chenxi Liu
[pdf] [arXiv]
[bibtex]
@InProceedings{Luo_2026_CVPR, author = {Luo, Xuewen and Yang, Fengze and Fan, Ding and Gao, Xiangbo and Yu, Bo and Li, Zihao and Tu, Zhengzhong and Zhou, Yang and Liu, Chenxi}, title = {V2X-UniPool: Unifying Multimodal Perception and Knowledge Reasoning for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {747-756} }

Calibration-Free View-Agnostic Monocular 3D Object Detection for Urban Scenes
Mehmet Kerem Turkcan,
Devika Gumaste,
Zoran Kostic
[pdf]
[bibtex]
@InProceedings{Turkcan_2026_CVPR, author = {Turkcan, Mehmet Kerem and Gumaste, Devika and Kostic, Zoran}, title = {Calibration-Free View-Agnostic Monocular 3D Object Detection for Urban Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {786-795} }

DRIVEXQA: Cross-modal Visual Question Answering for Adverse Driving Scene Understanding
Mingzhe Tao,
Ruiping Liu,
Junwei Zheng,
Yufan Chen,
Kedi Ying,
M. Saquib Sarfraz,
Kailun Yang,
Jiaming Zhang,
Rainer Stiefelhagen
[pdf] [arXiv]
[bibtex]
@InProceedings{Tao_2026_CVPR, author = {Tao, Mingzhe and Liu, Ruiping and Zheng, Junwei and Chen, Yufan and Ying, Kedi and Sarfraz, M. Saquib and Yang, Kailun and Zhang, Jiaming and Stiefelhagen, Rainer}, title = {DRIVEXQA: Cross-modal Visual Question Answering for Adverse Driving Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {775-785} }

Roadside LiDAR for Cooperative Safety Auditing at Urban Intersections: Toward Auditable V2X Infrastructure Intelligence
Bo Shang,
Yiqiao Li
[pdf] [arXiv]
[bibtex]
@InProceedings{Shang_2026_CVPR, author = {Shang, Bo and Li, Yiqiao}, title = {Roadside LiDAR for Cooperative Safety Auditing at Urban Intersections: Toward Auditable V2X Infrastructure Intelligence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {757-765} }

Importance-Driven 3D Gaussian SLAM for Efficient Mapping and Communication-Aware Sharing
Zhaolin Yang,
Huilin Yin,
Linchuan Zhang,
Mingyu Liu,
Alois C Knoll
[pdf]
[bibtex]
@InProceedings{Yang_2026_CVPR, author = {Yang, Zhaolin and Yin, Huilin and Zhang, Linchuan and Liu, Mingyu and Knoll, Alois C}, title = {Importance-Driven 3D Gaussian SLAM for Efficient Mapping and Communication-Aware Sharing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {796-804} }

Rethinking Intermediate Module Utilization in V2X End-to-End Autonomous Driving
Yiming Kan,
Huilin Yin,
Daniel Watzenig
[pdf]
[bibtex]
@InProceedings{Kan_2026_CVPR, author = {Kan, Yiming and Yin, Huilin and Watzenig, Daniel}, title = {Rethinking Intermediate Module Utilization in V2X End-to-End Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {728-736} }

4-D Radar Meets LiDAR and Camera: Cooperative Perception under Adverse Weather
Melih Yazgan,
Iramm Hamdard,
Qiyuan Wu,
Svetlana Pavlitska,
J. Marius Zöllner
[pdf]
[bibtex]
@InProceedings{Yazgan_2026_CVPR, author = {Yazgan, Melih and Hamdard, Iramm and Wu, Qiyuan and Pavlitska, Svetlana and Z\"ollner, J. Marius}, title = {4-D Radar Meets LiDAR and Camera: Cooperative Perception under Adverse Weather}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {805-814} }