ika-rwth-aachen/MultiCorrupt
[IV2024] MultiCorrupt: A benchmark for robust multi-modal 3D object detection, evaluating LiDAR-Camera fusion models in autonomous driving. Includes diverse corruption types (e.g., misalignment, miscalibration, weather) and severity levels. Assess model performance under challenging conditions.
Jupyter NotebookMIT
Issues
- 4
Error points generation in fog simulation
#13 opened by fdy61 - 6
Estimated Generation Time
#12 opened by curiosity654 - 2
About Reproducing CMT
#11 opened by curiosity654 - 1
Evaluate IS-Fusion
#4 opened by TillBeemelmanns - 0
Evaluate UniBEV
#7 opened by TillBeemelmanns - 3
- 2
Issues testing with the nuscenes mini : "This mmdetection3d version is not supported."
#10 opened by zarathacia - 1
Use lidar sweep when evaluating?
#8 opened by gigoug - 4
- 4
Evaluation of the robustness
#5 opened by Barath19 - 0
Evaluate AutoAlignV2
#3 opened by TillBeemelmanns - 8
Missing of the file for reproducibility
#2 opened by Barath19 - 2
Support for other datasets
#1 opened by Barath19