Visual Servoing on Hollywood poster (Unperturbed)
100Convergence RateDMLVS
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DMLVSMethod Type=Scene-specific finetuning2026.06 | 100 | 0 | 0 | — | — | |
| ViT-VS: DINOv2-308Method Type=Training-free: patch-level ViT, Backbone Architecture=DINOv2, Resolution / Tiling Configuration=3082026.06 | 100 | 1.86 | 1.5 | 1,254 | 15.1 | |
| ViT-VS: DINOv2-518Method Type=Training-free: patch-level ViT, Backbone Architecture=DINOv2, Resolution / Tiling Configuration=5182026.06 | 100 | 1.04 | 0.81 | 1,328 | 6.3 | |
| ViT-VS: DINOv3-1440Method Type=Training-free: patch-level ViT, Backbone Architecture=DINOv3, Resolution / Tiling Configuration=14402026.06 | 100 | 0.52 | 0.44 | 2,430 | 1.1 | |
| ART-VS: DINOv2-7x7Method Type=Training-free: patch-level ViT, Backbone Architecture=DINOv2, Resolution / Tiling Configuration=7x72026.06 | 100 | 0.74 | 0.64 | 2,172 | 15.9 | |
| ART-VS: DINOv3-6x6Method Type=Training-free: patch-level ViT, Backbone Architecture=DINOv3, Resolution / Tiling Configuration=6x62026.06 | 100 | 0.75 | 0.61 | 1,766 | 16.4 | |
| ART-VS: AM-Radio-6x6Method Type=Training-free: patch-level ViT, Backbone Architecture=AM-Radio, Resolution / Tiling Configuration=6x62026.06 | 100 | 0.87 | 0.74 | 2,778 | 15.8 | |
| ORB-IBVSMethod Type=Training-free: pixel-level descriptors2026.06 | 95.4 | 0.17 | 0.13 | — | 22.4 | |
| SIFT-IBVSMethod Type=Training-free: pixel-level descriptors2026.06 | 94.8 | 0.06 | 0.05 | — | 2.9 | |
| AKAZE-IBVSMethod Type=Training-free: pixel-level descriptors2026.06 | 90.6 | 0.03 | 0.03 | — | 2.1 | |
| PBVS-CNNMethod Type=Scene-specific finetuning, Backbone Architecture=CNN2026.06 | 75.6 | 3.35 | 1.71 | — | — |