Research Article
MANet: End-to-End Learning for Point Cloud Based on Robust Pointpillar and Multiattention
Table 4
Results on the test nuScenes 3D detection benchmark.
| Methods | Car | Pedestrian | Cyclist | mAP |
| Baseline [6] | 62.5 | 50.2 | 64.5 | 57.6 | PVRCNN | 64.8 | 46.7 | ā | ā | Centerpoint | 66.1 | 62.4 | 67.6 | 65.3 | Point augmenting | 62.2 | 64.6 | 73.3 | 66.7 | Ours | 65.1 | 63.7 | 65.9 | 64.9 |
|
|