Pose Estimation on SurgPose
69.7mAPMultiMAE
Evaluation Results
| Method | Links | |
|---|---|---|
| MultiMAEEvaluation Protocol=End-to-End Fine-tuning, Pre-training dataset=Surgical, Input Modality=RGB-D2026.01 | 69.7 | |
| SurfSurg6DSetting=syn+real2026.05 | 68.97 | |
| SurfSurg6DSetting=real2026.05 | 67.56 | |
| SurfembSetting=syn+real2026.05 | 63.85 | |
| MRC-NetSetting=syn+real2026.05 | 60.06 | |
| SurfembSetting=real2026.05 | 57.97 | |
| GDR-NetSetting=syn+real2026.05 | 52.01 | |
| DINOv2-RGBEvaluation Protocol=End-to-End Fine-tuning, Pre-training dataset=Surgical, Input Modality=RGB2026.01 | 51.4 | |
| MultiMAE (IN-1k)Evaluation Protocol=End-to-End Fine-tuning, Pre-training dataset=ImageNet-1k, Input Modality=RGB2026.01 | 51.4 | |
| DINOv2-RGBDEvaluation Protocol=End-to-End Fine-tuning, Pre-training dataset=Surgical, Input Modality=RGB-D2026.01 | 49.4 | |
| MAEEvaluation Protocol=End-to-End Fine-tuning, Pre-training dataset=Surgical, Input Modality=RGB2026.01 | 48.1 | |
| DINOv2 (LVD)Evaluation Protocol=End-to-End Fine-tuning, Pre-training dataset=LVD, Input Modality=RGB2026.01 | 47.9 | |
| GDR-NetSetting=real2026.05 | 46.93 | |
| Mask3DEvaluation Protocol=End-to-End Fine-tuning, Input Modality=Point Cloud2026.01 | 46.3 | |
| MAE (IN-1k)Evaluation Protocol=End-to-End Fine-tuning, Pre-training dataset=ImageNet-1k, Input Modality=RGB2026.01 | 43.6 | |
| MRC-NetSetting=real2026.05 | 26.78 | |
| FoundPoseSetting=zero-shot2026.05 | 9.76 | |
| MegaPoseSetting=zero-shot2026.05 | 0.3 |