3D Semantic Segmentation on S3DIS (all six areas)
88.5Overall Accuracy (OA)MuGNet
Evaluation results
| Method | Links | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MuGNet2020.09 | 88.5 | 69.8 | 92 | 95.7 | 82.5 | 64.4 | 60.1 | 60.7 | 69.7 | 82.6 | 70.3 | 64.4 | 52.1 | 52.8 | 60.6 | |
| RandLA-Net2020.09 | 88 | 70 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SPG2020.09 | 85.5 | 62.1 | 89.9 | 95.1 | 76.4 | 62.8 | 47.1 | 55.3 | 68.4 | 73.5 | 69.2 | 63.2 | 45.9 | 8.7 | 52.9 | |
| DGCNN2020.09 | 84.1 | 56.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Engelmann et al.2020.09 | 81.1 | 49.7 | 90.3 | 92.1 | 67.9 | 44.7 | 24.2 | 52.3 | 51.2 | 47.4 | 58.1 | 39 | 6.9 | 30 | 41.9 | |
| PointNet2020.09 | 78.5 | 47.6 | 88 | 88.7 | 69.3 | 42.4 | 23.1 | 47.5 | 51.6 | 42 | 54.1 | 38.2 | 9.6 | 29.4 | 35.2 |