Object Pose Estimation on Occluded-LINEMOD Average Seen
83.4Accuracy (Acc@15)context-aware weight aggregation network
Evaluation results
| Method | Links | |
|---|---|---|
| context-aware weight aggregation networkBackbone=SD-V2-0, Aggregation=CWA2024.03 | 83.4 | |
| nonlinear aggregation networkBackbone=SD-V1-5, Aggregation=NA2024.03 | 83.3 | |
| context-aware weight aggregation networkBackbone=DINOv2, Aggregation=CWA2024.03 | 83.1 | |
| context-aware weight aggregation networkBackbone=SD-V1-5, Aggregation=CWA2024.03 | 82.8 | |
| vanilla aggregation networkBackbone=SD-V1-5, Aggregation=VA2024.03 | 82.5 | |
| context-aware weight aggregation networkBackbone=OpenCLIP, Aggregation=CWA2024.03 | 81.9 | |
| Template-poseBackbone=ResNet2024.03 | 79.4 | |
| Zhao et al.Backbone=ResNet2024.03 | 56.1 | |
| MPLBackbone=MPL2024.03 | 31.7 | |
| Wohlhart et al.Backbone=Wohlhart et al.2024.03 | 19.5 | |
| Balntas et al.Backbone=Wohlhart et al.2024.03 | 19.1 |