Image Based Localization On Cvusa 1
评估指标
Recall@1
Recall@10
Recall@5
Recall@top1%
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | |||||
|---|---|---|---|---|---|---|
| CV-Cities | 99.19 | 99.85 | 99.80 | 99.92 | CV-Cities: Advancing Cross-View Geo-Localization in Global Cities | |
| Sample4Geo | 98.68 | 99.78 | 99.68 | 99.87 | Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation | |
| SAIG-D | 96.34 | 99.50 | 99.10 | 99.86 | Simple, Effective and General: A New Backbone for Cross-view Image Geo-localization | |
| GeoDTR | 95.43 | 99.34 | 98.86 | 99.86 | Beyond Geo-localization: Fine-grained Orientation of Street-view Images by Cross-view Matching with Satellite Imagery with Supplementary Materials | - |
| Transgeo | 94.08 | 99.04 | 98.36 | 99.77 | TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization | |
| LPN | 85.79 | 96.98 | 95.38 | 99.41 | Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization | |
| RK-Net | 52.50 | - | - | 96.52 | Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization | - |
| Instance Loss | 43.91 | 74.58 | 66.38 | 91.78 | University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization |
0 of 8 row(s) selected.