Cloud Removal on Multi-temporal Real-world Cloud-degraded Scenes Hubei
27.188PSNRPhyVLM-CR
Evaluation results
| Method | Links | ||
|---|---|---|---|
| PhyVLM-CRProtocol=T1 input, T2 ground truth, T3 auxiliary reference2026.03 | 27.188 | 92.2 | |
| Traditional PhysicalProtocol=T1 input, T2 ground truth, T3 auxiliary reference2026.03 | 19.701 | 73.13 | |
| Vision-Language ModelProtocol=T1 input, T2 ground truth, T3 auxiliary reference2026.03 | 18.937 | 56.55 | |
| Zero-shot Deep LearningProtocol=T1 input, T2 ground truth, T3 auxiliary reference2026.03 | 14.568 | 30.42 |