Object Pose Estimation on LINEMOD (LM) 1.0 (Split #1 Unseen)
98.4Accuracy (Acc15)context-aware weight aggregation network
Evaluation Results
| Method | Links | |
|---|---|---|
| context-aware weight aggregation networkBackbone=SD-V2-0 [32], Aggregation=CWA2024.03 | 98.4 | |
| context-aware weight aggregation networkBackbone=SD-V1-5 [32], Aggregation=CWA2024.03 | 98.3 | |
| context-aware weight aggregation networkBackbone=SD-V2-0 [32], Aggregation=CWA2024.03 | 98.1 | |
| context-aware weight aggregation networkBackbone=SD-V1-5 [32], Aggregation=CWA2024.03 | 97.9 | |
| context-aware weight aggregation networkBackbone=DINOV2 [26], Aggregation=CWA2024.03 | 97.8 | |
| nonlinear aggregation networkBackbone=SD-V1-5 [32], Aggregation=NA2024.03 | 97.7 | |
| nonlinear aggregation networkBackbone=SD-V1-5 [32], Aggregation=NA2024.03 | 97.5 | |
| vanilla aggregation networkBackbone=SD-V1-5 [32], Aggregation=VA2024.03 | 97.4 | |
| vanilla aggregation networkBackbone=SD-V1-5 [32], Aggregation=VA2024.03 | 97.4 | |
| context-aware weight aggregation networkBackbone=OpenCLIP [31], Aggregation=CWA2024.03 | 97.1 | |
| context-aware weight aggregation networkBackbone=OpenCLIP [31], Aggregation=CWA2024.03 | 97 | |
| context-aware weight aggregation networkBackbone=DINOV2 [26], Aggregation=CWA2024.03 | 96.6 | |
| Template-poseBackbone=ResNet [8]2024.03 | 94.4 | |
| Template-poseBackbone=ResNet [8]2024.03 | 93.5 | |
| Zhao et al.Backbone=ResNet [8]2024.03 | 87.5 | |
| Zhao et al.Backbone=ResNet [8]2024.03 | 79.2 | |
| MPLBackbone=MPL [36]2024.03 | 38.3 | |
| MPLBackbone=MPL [36]2024.03 | 36 | |
| Wohlhart et al.Backbone=Wohlhart et al. [40]2024.03 | 16.7 | |
| Balntas et al.Backbone=Wohlhart et al. [40]2024.03 | 15.2 | |
| Wohlhart et al.Backbone=Wohlhart et al. [40]2024.03 | 14.1 | |
| Balntas et al.Backbone=Wohlhart et al. [40]2024.03 | 13.2 |