3D Object Detection On Nuscenes
Métriques
NDS
mAAE
mAOE
mAP
mASE
mATE
mAVE
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | NDS | mAAE | mAOE | mAP | mASE | mATE | mAVE | Paper Title | Repository |
---|---|---|---|---|---|---|---|---|---|
xin.lu.2 | 0.52 | 0.13 | 0.42 | 0.43 | 0.26 | 0.6 | 0.5 | - | - |
LargeKernel-F | 0.74 | 0.13 | 0.3 | 0.71 | 0.23 | 0.24 | 0.24 | - | - |
pcd_lidar_99 | 0.7 | 0.13 | 0.34 | 0.64 | 0.24 | 0.26 | 0.22 | - | - |
MVP | 0.71 | 0.13 | 0.32 | 0.66 | 0.24 | 0.26 | 0.31 | Multimodal Virtual Point 3D Detection | |
3D Dual-Fusion | 0.71 | 0.12 | 0.36 | 0.68 | 0.24 | 0.27 | 0.26 | - | - |
SECOND + PointPillars | 0.18 | 0.59 | 0.96 | 0.09 | 0.42 | 0.7 | 1.0 | - | - |
pointpainting | 0.61 | 0.13 | 0.54 | 0.54 | 0.26 | 0.38 | 0.29 | - | - |
TiG-BEV | 0.62 | 0.13 | 0.34 | 0.53 | 0.24 | 0.45 | 0.31 | - | - |
weareateam | 0.38 | 0.18 | 0.54 | 0.3 | 0.27 | 0.72 | 1.17 | - | - |
Deeplearner | 0.73 | 0.13 | 0.34 | 0.71 | 0.24 | 0.25 | 0.26 | - | - |
BEVFusion | 0.72 | 0.13 | 0.37 | 0.69 | 0.25 | 0.26 | 0.27 | - | - |
Vidar | 0.45 | 0.13 | 0.44 | 0.38 | 0.25 | 0.63 | 1.48 | - | - |
CenterFusion | 0.45 | 0.11 | 0.52 | 0.33 | 0.26 | 0.63 | 0.61 | - | - |
PGD | 0.45 | - | - | 0.39 | - | - | - | Probabilistic and Geometric Depth: Detecting Objects in Perspective | |
DAMEN | 0.58 | 0.12 | 0.39 | 0.46 | 0.25 | 0.46 | 0.33 | - | - |
picolo | 0.71 | 0.12 | 0.37 | 0.67 | 0.24 | 0.27 | 0.27 | - | - |
ASCNet-1-5s | 0.57 | 0.14 | 0.42 | 0.45 | 0.25 | 0.32 | 0.42 | - | - |
obj_4 | 0.59 | 0.14 | 0.38 | 0.51 | 0.26 | 0.45 | 0.39 | - | - |
yangfan293 | 0.61 | 0.15 | 0.43 | 0.54 | 0.26 | 0.4 | 0.36 | - | - |
Radiant | 0.58 | 0.42 | 0.33 | 0.62 | 0.24 | 0.28 | 1.35 | - | - |
0 of 372 row(s) selected.