Research map / Detection and segmentation / 3D detection and driving
V2XScenes: A Multiple Challenging Traffic Conditions Dataset for Large-Range Vehicle-Infrastructure Collaborative Perception
Bowen Wang, Yafei Wang, Wei Gong, Siheng Chen, Genjia Liu, Minhao Xiong, Chin Long Ng
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 CoBEVT intermediate fusion to the single vehicle (no fusion) (ablation) | PointPillars detector · V2XScenes rainy car detection (IoU=0.5) | AP3D: 29.82 -> 63.79 | Improved |
| add late fusion to the single vehicle in heavy rain (ablation) | PointPillars detector · V2XScenes rainy car detection (IoU=0.7) | AP3D: 13.15 -> 6.33 | Hurt |
| add Where2Comm fusion to the single vehicle in sunny scenes (ablation) | PointPillars detector · V2XScenes sunny car detection (IoU=0.7) | AP3D: 47.15 -> 45.18 | Hurt |
| add AttuFuse fusion in rain (ablation) | PointPillars detector · V2XScenes rainy car detection (IoU=0.7) | AP3D: 13.15 -> 12.08 | Hurt |
| add early fusion to the single vehicle in sunny scenes (ablation) | PointPillars detector · V2XScenes sunny car detection (IoU=0.7) | AP3D: 47.15 -> 59.91 | Improved |
| add F-Cooper intermediate fusion in rain (ablation) | PointPillars detector · V2XScenes rainy car detection (IoU=0.5) | AP3D: 29.82 -> 55.68 | Improved |
| use V2XViT intermediate fusion instead of early fusion | V2XViT · V2XScenes cooperative 3D detection (IoU=0.7) | AP3D: 10.31 -> 26.48 | Improved |
| use early fusion instead of late fusion at loose IoU | Early Fusion · V2XScenes cooperative 3D detection (IoU=0.3) | AP3D: 39.97 -> 35.59 | Hurt |
| use CoBEVT sparse attention for rainy feature-sparse conditions (ablation) | CoBEVT · V2XScenes rainy car detection (IoU=0.3) | AP3D: 38.72 -> 73.33 | Improved |
| increase transmission latency (ablation) | V2X intermediate fusion methods · V2XScenes cooperative 3D detection | AP3D | Hurt |
| use ISN tracker with occlusion model instead of other trackers | ISN · V2XScenes roadside tracking | MOTA: +8.0% MOTA, +14.4% MOTP | Improved |
| rainy weather instead of sunny for LiDAR sensing | Car detection, no fusion · V2XScenes car detection (IoU=0.5) | AP3D: 68.89 -> 29.82 | 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 0.90)
- TUMTraf V2X Cooperative Perception Dataset (CVPR 2024 · similarity 0.89)
- RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception (CVPR 2024 · similarity 0.89)
- RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions (CVPR 2025 · similarity 0.89)
- AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios (NeurIPS 2025 · similarity 0.88)
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.
