Bird's Eye View Object Detection on KITTI official leaderboard (test)
33.6APBEV (Easy)MonoDETR
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MonoDETRExtra data=None2022.03 | 33.6 | 22.11 | 18.6 | |
| AutoShapeExtra data=CAD2022.03 | 30.66 | 20.08 | 15.59 | |
| MonoDTRExtra data=LiDAR2022.03 | 28.59 | 20.38 | 17.14 | |
| MonoFlexExtra data=None2022.03 | 28.23 | 19.75 | 16.89 | |
| DDMP-3DExtra data=Depth2022.03 | 28.08 | 17.89 | 13.44 | |
| MonoRUnExtra data=LiDAR2022.03 | 27.94 | 17.34 | 15.24 | |
| CaDDNExtra data=LiDAR2022.03 | 27.94 | 18.91 | 17.19 | |
| PGDExtra data=None2022.03 | 26.89 | 16.51 | 13.49 | |
| Kinematic3DInput Modality=image + video, Inference Time (ms)=1202021.04 | 26.69 | 17.52 | 13.1 | |
| Kinematic3DExtra data=Video2022.03 | 26.69 | 17.52 | 13.1 | |
| IAFAExtra data=None2022.03 | 25.88 | 17.88 | 15.35 | |
| MonoGeoExtra data=None2022.03 | 25.86 | 18.99 | 16.19 | |
| MonoRCNNInput Modality=image, Inference Time (ms)=70, Backbone=ResNet-502021.04 | 25.48 | 18.11 | 14.1 | |
| MonoRCNNExtra data=None2022.03 | 25.48 | 18.11 | 14.1 | |
| AM3DInput Modality=image + depth, Inference Time (ms)=400, Backbone=ResNet-1012021.04 | 25.03 | 17.32 | 14.91 | |
| MonoDLEExtra data=None2022.03 | 24.79 | 18.89 | 16 | |
| DA-3DdetInput Modality=image + depth, Inference Time (ms)=400, Backbone=ResNet-1012021.04 | 23.35 | 15.9 | 12.11 | |
| PatchNetInput Modality=image + depth, Inference Time (ms)=400, Backbone=ResNet-1012021.04 | 22.97 | 16.86 | 14.97 | |
| PatchNetExtra data=Depth2022.03 | 22.97 | 16.86 | 14.97 | |
| MoVi-3DInput Modality=image2021.04 | 22.76 | 17.03 | 14.85 | |
| D4LCNInput Modality=image + depth, Inference Time (ms)=200, Backbone=ResNet-1012021.04 | 22.51 | 16.02 | 12.55 | |
| D4LCNExtra data=Depth2022.03 | 22.51 | 16.02 | 12.55 | |
| M3D-RPNInput Modality=image, Inference Time (ms)=160, Backbone=DenseNet-1212021.04 | 21.02 | 13.67 | 10.23 | |
| SMOKEExtra data=None2022.03 | 20.83 | 14.49 | 12.75 | |
| MonoPairInput Modality=image, Inference Time (ms)=60, Backbone=DLA-342021.04 | 19.28 | 14.83 | 12.89 | |
| MonoPairExtra data=None2022.03 | 19.28 | 14.83 | 12.89 | |
| RTM3DInput Modality=image, Inference Time (ms)=50, Backbone=DLA-34, Training Images=additional images from right cameras2021.04 | 19.17 | 14.2 | 11.99 | |
| ROI-10DInput Modality=image + depth, Inference Time (ms)=2002021.04 | 9.78 | 4.91 | 3.74 | |
| FQNetInput Modality=image, Inference Time (ms)=5002021.04 | 5.4 | 3.23 | 2.46 |