Table 4.
Evaluation performance regarding for semantic segmentation on the ShapeNet part dataset [6,45,46,48,51,58,59,81].
| Intersection over Union (IoU) | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Mean | Air- Place | Bag | Cap | Car | Chair | Ear- Phone | Guitar | Knife | |
| PointNet [6] | 83.7 | 83.4 | 78.7 | 82.5 | 74.9 | 89.6 | 73.0 | 91.5 | 85.9 |
| PointNet++ [43] | 85.1 | 82.4 | 79.0 | 87.7 | 77.3 | 90.8 | 71.8 | 91.0 | 85.9 |
| SO-Net [57] | 84.6 | 81.9 | 83.5 | 84.8 | 78.1 | 90.8 | 72.2 | 90.1 | 83.6 |
| Dynamic Graph CNN [49] | 85.1 | 84.2 | 83.7 | 84.4 | 77.1 | 90.9 | 78.5 | 91.5 | 87.3 |
| Kd-Net [78] | 82.3 | 80.1 | 74.6 | 74.3 | 70.3 | 88.6 | 73.5 | 90.2 | 87.2 |
| 3DContextNet [44] | 84.3 | 83.3 | 78.0 | 84.2 | 77.2 | 90.1 | 73.1 | 91.6 | 85.9 |
| MRTNet [46] | 79.3 | 81.0 | 76.7 | 87.0 | 73.8 | 89.1 | 67.6 | 90.6 | 85.4 |
| SPLATNet [56] | 83.7 | 85.4 | 83.2 | 84.3 | 89.1 | 80.3 | 90.7 | 75.5 | 93.1 |