Object Pose Estimation on Occluded-LINEMOD (Average Unseen)
0.859Acc@15context-aware weight aggregation network
Evaluation Results
| Method | Links | |
|---|---|---|
| context-aware weight aggregation networkBackbone=SD-V1-5, Aggregation=CWA2024.03 | 0.859 | |
| nonlinear aggregation networkBackbone=SD-V1-5, Aggregation=NA2024.03 | 0.855 | |
| context-aware weight aggregation networkBackbone=SD-V2-0, Aggregation=CWA2024.03 | 0.852 | |
| vanilla aggregation networkBackbone=SD-V1-5, Aggregation=VA2024.03 | 0.846 | |
| context-aware weight aggregation networkBackbone=OpenCLIP, Aggregation=CWA2024.03 | 0.811 | |
| context-aware weight aggregation networkBackbone=DINOv2, Aggregation=CWA2024.03 | 0.781 | |
| Template-poseBackbone=ResNet2024.03 | 0.763 | |
| Zhao et al.Backbone=ResNet2024.03 | 0.368 | |
| MPLBackbone=MPL2024.03 | 0.174 | |
| Wohlhart et al.Backbone=Wohlhart et al.2024.03 | 0.078 | |
| Balntas et al.Backbone=Wohlhart et al.2024.03 | 0.065 |