Performance comparison with state-of-the-art models on the Nuscenes val set for all 10 classes and all the 3D detection results are evaluated with average precision.
| Models | Car | Truck | CV | Bus | Trailer | Barrier | Motor. | Cyc. | Ped. | Cone |
|---|---|---|---|---|---|---|---|---|---|---|
| Voxel-RCNN, [6] | 68.88 | 28.03 | 6.04 | 54.34 | 17.99 | 25.37 | 22.39 | 7.21 | 59.55 | 25.39 |
| Ours | 69.25 | 28.95 | 6.83 | 54.31 | 18.04 | 26.57 | 23.75 | 8.46 | 59.56 | 25.08 |
| Models | Car | Truck | CV | Bus | Trailer | Barrier | Motor. | Cyc. | Ped. | Cone |
|---|---|---|---|---|---|---|---|---|---|---|
| Voxel-RCNN, [ | 68.88 | 28.03 | 6.04 | 54.34 | 17.99 | 25.37 | 22.39 | 7.21 | 59.55 | 25.39 |
| Ours | 69.25 | 28.95 | 6.83 | 54.31 | 18.04 | 26.57 | 23.75 | 8.46 | 59.56 | 25.08 |
Note: The above results are reproduced by the publicly release model ([28]). Note that CV stands for construction vehicle and Cone for traffic cone.
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.