nuScenes
A large-scale autonomous driving perception benchmark dataset released by Motional (formerly nuTonomy). It includes multi-camera, LiDAR, and radar data and is widely used for standardized evaluation of 3D object detection and tracking.
Timeline (last 90 days)
On the pedestrian trajectory forecasting task, eCoMAE achieved the best fine-tuned MSE on all four datasets: IMPTC, Waymo, nuScenes and inD.
The study uses a PointPillars ensemble model and conducts experiments on two public datasets, KITTI and nuScenes.
When counting by frame, the same data yields "not applicable" results under pre-fixed limits for long-range transfer, rainy transfer, and transfer between two independently trained detectors.
When counting by recorded sequence, neither dataset provides enough independent units to support any performance target limit, and no transfer yields a "not applicable" result.
GeoState achieves zero-shot generalization on the KITTI and nuScenes datasets, transferring to different sensor configurations and scene distributions without retraining on new datasets.
nuScenes was released by Motional (formerly nuTonomy) and contains LiDAR and multi-camera data from Boston and Singapore.
MESSENGER achieves state-of-the-art performance on nuScenes and Argoverse 2.
In the long-horizon future extrapolation task on the nuScenes dataset, MESSENGER reduces the 3D endpoint error (EPE3D) by 71.6%.
A handful of datasets such as ImageNet, nuScenes, KITTI, and Waymo Open Dataset have long dominated evaluation leaderboards for autonomous driving perception, detection, and planning tasks.
The KITTI and nuScenes benchmarks both report detection metrics separately by distance intervals such as 0–30 m, 30–50 m, and 50 m and above.
All Facts (10)
On the pedestrian trajectory forecasting task, eCoMAE achieved the best fine-tuned MSE on all four datasets: IMPTC, Waymo, nuScenes and inD.
50%UnverifiedThe study uses a PointPillars ensemble model and conducts experiments on two public datasets, KITTI and nuScenes.
50%UnverifiedWhen counting by frame, the same data yields "not applicable" results under pre-fixed limits for long-range transfer, rainy transfer, and transfer between two independently trained detectors.
50%UnverifiedWhen counting by recorded sequence, neither dataset provides enough independent units to support any performance target limit, and no transfer yields a "not applicable" result.
50%UnverifiedGeoState achieves zero-shot generalization on the KITTI and nuScenes datasets, transferring to different sensor configurations and scene distributions without retraining on new datasets.
50%UnverifiednuScenes was released by Motional (formerly nuTonomy) and contains LiDAR and multi-camera data from Boston and Singapore.
50%UnverifiedMESSENGER achieves state-of-the-art performance on nuScenes and Argoverse 2.
50%UnverifiedIn the long-horizon future extrapolation task on the nuScenes dataset, MESSENGER reduces the 3D endpoint error (EPE3D) by 71.6%.
50%UnverifiedA handful of datasets such as ImageNet, nuScenes, KITTI, and Waymo Open Dataset have long dominated evaluation leaderboards for autonomous driving perception, detection, and planning tasks.
50%UnverifiedThe KITTI and nuScenes benchmarks both report detection metrics separately by distance intervals such as 0–30 m, 30–50 m, and 50 m and above.
50%