3D object segmentation on KITTI-Det (val)
95.8APVoxel-RCNN
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Voxel-RCNNSupervision=Supervised, Training dataset=KITTI-Det2022.10 | 95.8 | 79.6 | 87.3 | 78.1 | 98.9 | 92.6 | 97.3 | |
| PointRCNNSupervision=Supervised, Training dataset=KITTI-Det2022.10 | 95.7 | 80.1 | 88.9 | 81.3 | 98 | 91.4 | 97.2 | |
| PV-RCNNSupervision=Supervised, Training dataset=KITTI-Det2022.10 | 95.4 | 77.3 | 84.4 | 73.7 | 98.8 | 92.7 | 97.1 | |
| OGCsupSupervision=Supervised, Training dataset=KITTI-Det2022.10 | 80 | 68.5 | 78.3 | 72.7 | 84.8 | 84 | 96.9 | |
| OGC*supSupervision=Supervised, Training dataset=KITTI-SF2022.10 | 51.4 | 41 | 49.1 | 43.7 | 56 | 66.2 | 91 | |
| OGC*(Ours)Supervision=Unsupervised, Training dataset=KITTI-SF2022.10 | 40.5 | 30.9 | 37 | 30.8 | 46.5 | 60.6 | 86.4 |