3D Instance Segmentation On Scannet200
Metrics
mAP
mAP@25
mAP@50
Results
Performance results of various models on this benchmark
Model Name | mAP | mAP@25 | mAP@50 | Paper Title | Repository |
|---|---|---|---|---|---|
| MSTA3D | 26.2 | 40.1 | 35.2 | MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation | - |
| ODIN | 31.5 | 53.1 | 45.3 | ODIN: A Single Model for 2D and 3D Segmentation | |
| ISBNet | 24.5 | - | - | ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution | |
| Open3DIS (Open-Vocabulary) | 23.7 | - | - | Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance | |
| Mask3D | 27.8 | - | - | Mask3D: Mask Transformer for 3D Semantic Instance Segmentation |
0 of 5 row(s) selected.