Panoptic Segmentation On Scannetv2
Metrics
PQ
Results
Performance results of various models on this benchmark
Model Name | PQ | Paper Title | Repository |
|---|---|---|---|
| PanopticNDT (10cm) | 59.19 | PanopticNDT: Efficient and Robust Panoptic Mapping | |
| OneFormer3D | 71.2 | OneFormer3D: One Transformer for Unified Point Cloud Segmentation | |
| SceneGraphFusion (NN mapping) | 31.5 | SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences | |
| SuperCluster | 58.7 | Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering | |
| PanopticFusion (with CRF) | 33.5 | PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things | - |
0 of 5 row(s) selected.