Object Pose Estimation on Occluded-LINEMOD (Split #3 Seen)
80.8Accuracy (Acc15)context-aware weight aggregation network
Evaluation Results
| Method | Links | |
|---|---|---|
| context-aware weight aggregation networkBackbone=SD-V1-5, Aggregation=CWA2024.03 | 80.8 | |
| vanilla aggregation networkBackbone=SD-V1-5, Aggregation=VA2024.03 | 80.2 | |
| context-aware weight aggregation networkBackbone=OpenCLIP, Aggregation=CWA2024.03 | 80.1 | |
| nonlinear aggregation networkBackbone=SD-V1-5, Aggregation=NA2024.03 | 79.5 | |
| context-aware weight aggregation networkBackbone=SD-V2-0, Aggregation=CWA2024.03 | 79.2 | |
| context-aware weight aggregation networkBackbone=DINOv2, Aggregation=CWA2024.03 | 79 | |
| Template-poseBackbone=ResNet2024.03 | 76.8 | |
| Zhao et al.Backbone=ResNet2024.03 | 49.9 | |
| MPLBackbone=MPL2024.03 | 29.2 | |
| Wohlhart et al.Backbone=Wohlhart et al.2024.03 | 17.6 | |
| Balntas et al.Backbone=Wohlhart et al.2024.03 | 15 |