TUMTraf V2X Cooperative Perception Dataset
Paper • 2403.01316 • Published
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
TUMTraf CoopDet3D Base Pretrained — 3rd Place @ DriveX 2026
Model Overview
- Architecture: CoopDet3D (Camera + LiDAR cooperative fusion)
- Source: Official pretrained weights from TUMTraf paper authors (CVPR 2024)
- Paper: TUMTraf V2X Cooperative Perception Dataset (CVPR 2024)
Results (CodaBench — Final Submission)
| Class | AP |
|---|---|
| BUS | 1.000 |
| BICYCLE | 0.866 |
| PEDESTRIAN | 0.696 |
Competition
- Challenge: 2026 DriveX Grand Challenge — TUMTraf V2X Cooperative Perception
- Final mAP: 0.9062 (3rd Place internationally)
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support