Image Registration on VIS-XR Set2 scale 3.0-3.8 (lowest resolution level)
0.64MECN+R+LG
Evaluation results
| Method | Links | ||
|---|---|---|---|
| CN+R+LGEstimation Method=DLT, Post-processing=VFC2026.01 | 0.64 | 2.37 | |
| CN+LGEstimation Method=DLT, Post-processing=VFC2026.01 | 0.69 | 2.96 | |
| SP+LG-PEstimation Method=DLT, Fine-tuning=on Multi-modal Panel Painting dataset, Post-processing=VFC2026.01 | 0.77 | 3.88 | |
| Roma-MiEstimation Method=Magsac, Post-processing=VFC2026.01 | 0.87 | 5.13 | |
| Roma-MaEstimation Method=Magsac, Post-processing=VFC2026.01 | 0.97 | 5.46 | |
| Aliked+LG-PEstimation Method=DLT, Fine-tuning=on Multi-modal Panel Painting dataset, Post-processing=VFC2026.01 | 1.11 | 4.6 | |
| Roma-OEstimation Method=Magsac, Post-processing=VFC2026.01 | 1.65 | 7.96 | |
| LoFTR-MiEstimation Method=Magsac, Post-processing=VFC2026.01 | 2.84 | 12.49 | |
| LoFTR-OEstimation Method=Magsac, Post-processing=VFC2026.01 | 4.7 | 18.32 | |
| LoFTR-PEstimation Method=Magsac, Fine-tuning=on Multi-modal Panel Painting dataset, Post-processing=VFC2026.01 | 32.97 | 206.09 |