3-DoF Camera Pose Estimation on KITTI Same-area
5.47Position Mean Error (m)VIRD
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| VIRDBackbone=VGG162026.03 | 5.47 | 2.07 | 79.46 | 98.3 | 31.65 | 75.78 | 5.16 | 1.02 | 49.32 | 92.95 | |
| VIRDBackbone=EfficientNet-B02026.03 | 5.55 | 2.22 | 79.43 | 98.41 | 29.84 | 73.89 | 4.87 | 0.98 | 51.2 | 92.82 | |
| FG2*Backbone=DINOv2 [15]2026.03 | 5.81 | 4.26 | 24.97 | 75.78 | 24.57 | 75.14 | 89.64 | 90.26 | 0.42 | 2.73 | |
| DenseFlow*Backbone=ResNet18 [6]2026.03 | 6.47 | 4.26 | 73.87 | 97.27 | 14.82 | 58.5 | 3.72 | 0.99 | 50.62 | 90.06 | |
| CCVPEBackbone=EfficientNet-B02026.03 | 6.88 | 3.47 | 53.3 | 85.13 | 25.84 | 68.49 | 15.01 | 6.12 | 8.96 | 42.75 | |
| SliceMatchBackbone=VGG162026.03 | 9.39 | 5.41 | 39.73 | 87.92 | 13.63 | 49.22 | 8.71 | 4.42 | 11.35 | 55.82 | |
| HighlyAccurateBackbone=VGG162026.03 | 15.51 | 15.97 | 5.17 | 25.44 | 4.66 | 25.39 | 89.91 | 90.75 | 0.61 | 2.89 |