Research map / Detection and segmentation / 3D detection and driving
V2X-Real: a Largs-Scale Dataset for Vehicle-to-Everything Cooperative Perception
Hao Xiang, Xin Xia, Zhaoliang Zheng, Runsheng Xu, Letian Gao, Zewei Zhou, xu han, Xinkai Ji, Mingxi Li, Zonglin Meng, Li Jin, Mingyue Lei and 6 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add cooperative fusion (any method) over No Fusion (ablation) | PointPillar detector · V2X-Real (all four subsets) | mAP: V2X-Real-I2I mAP@0.3 34.3 -> 62.7 (V2X-ViT) | Improved |
| use intermediate fusion instead of late or early fusion (ablation) | cooperative 3D detection · V2X-Real | mAP: V2X-Real-V2V mAP@0.3 38.1 -> 46.5 (V2X-ViT) | Mixed |
| use late fusion instead of No Fusion for pedestrians at IoU 0.5 (ablation) | V2X-Real-VC · V2X-Real-VC | AP pedestrian@IoU0.5: 13.1 -> 11.8 | Hurt |
| use late fusion instead of early fusion on infrastructure-to-infrastructure (ablation) | V2X-Real-I2I · V2X-Real-I2I | mAP@IoU0.3: 46.9 -> 52.2 | Improved |
| use F-Cooper instead of No Fusion in infrastructure-centric setting (ablation) | V2X-Real-IC · V2X-Real-IC | mAP@IoU0.3: 30.0 -> 37.5 | Improved |
| report pedestrian and truck classes in addition to car | V2X cooperative detection · V2X-Real-VC | AP: car 62.7 vs pedestrian 36.7 vs truck 35.1 AP@0.3 (V2X-ViT) | Hurt |
Closest papers by meaning
- V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception (NeurIPS 2025 · similarity 0.92)
- UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception (NeurIPS 2025 · similarity 0.92)
- End-to-End Autonomous Driving Through V2X Cooperation (AAAI 2025 · similarity 0.90)
- Privacy-Preserving V2X Collaborative Perception Integrating Unknown Collaborators (AAAI 2025 · similarity 0.90)
- BEVSync: Asynchronous Data Alignment for Camera-based Vehicle-Infrastructure Cooperative Perception Under Uncertain Delays (AAAI 2025 · similarity 0.90)
- TUMTraf V2X Cooperative Perception Dataset (CVPR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
