Visual Navigation on CAST (val)
1.65ATE XY RMSE (m)PiJEPA
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| PiJEPABackbone=V-JEPA-2 ViT-L2026.03 | 1.65 | 1.32 | 2.88 | 19.13 | 15.95 | 27.93 | 0.53 | 0.49 | 6.46 | 5.62 | |
| Octo-WMBackbone=V-JEPA-2 ViT-L2026.03 | 1.67 | 1.35 | 2.87 | 20.63 | 17.27 | 28.06 | 0.54 | 0.49 | 6.93 | 5.99 | |
| OctoBackbone=V-JEPA-2 ViT-L2026.03 | 1.72 | 1.36 | 3.02 | 18.72 | 15.64 | 27.72 | 0.53 | 0.48 | 6.09 | 5.34 | |
| PiJEPAEncoder backbone=DINOv2 ViT-S2026.03 | 1.78 | 1.42 | 3.12 | 19.89 | 16.52 | 28.63 | 0.56 | 0.51 | 7.05 | 6.07 | |
| Octo-WMEncoder backbone=DINOv2 ViT-S2026.03 | 1.8 | 1.43 | 3.15 | 22.16 | 18.6 | 29.16 | 0.56 | 0.51 | 7.51 | 6.45 | |
| MPPIEncoder backbone=DINOv2 ViT-S2026.03 | 1.85 | 1.48 | 3.23 | 18.79 | 15.68 | 27.86 | 0.55 | 0.51 | 5.7 | 5.11 | |
| MPPIBackbone=V-JEPA-2 ViT-L2026.03 | 1.87 | 1.5 | 3.29 | 19.15 | 15.98 | 28.5 | 0.55 | 0.52 | 5.75 | 5.15 | |
| OctoEncoder backbone=DINOv2 ViT-S2026.03 | 1.98 | 1.65 | 3.19 | 20.08 | 16.76 | 28.55 | 0.61 | 0.57 | 8.29 | 6.94 |