Panoptic Segmentation On Scannet
Metrics
PQ
PQ_st
PQ_th
Results
Performance results of various models on this benchmark
Model Name | PQ | PQ_st | PQ_th | Paper Title | Repository |
|---|---|---|---|---|---|
| PanopticFusion | 33.5 | 58.4 | 30.8 | PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things | - |
| SceneGraphFusion | 31.5 | 43.4 | 30.2 | SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences | |
| SuperCluster | 58.7 | 84.1 | 69.1 | Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering | |
| OneFormer3D | 71.2 | 86.1 | 69.6 | OneFormer3D: One Transformer for Unified Point Cloud Segmentation |
0 of 4 row(s) selected.