Beyond Local Refinement: Wide-Area Precise Cross-View Localization
Organizations: Xiamen University · University of Macau · Tsinghua University
Abstract
Fine-grained cross-view localization aims to precisely localize a ground camera against geo-referenced aerial imagery, but current methods typically assume a narrow geographic prior, substantially limiting their applicability when upstream localization remains coarse. To bridge this gap, we study this task over much larger aerial regions. However, this seemingly simple extension fundamentally changes the localization problem: the growing disparity in spatial extent between ground and aerial views makes reliable cross-view matching difficult to establish directly, while the increasing number of look-alike locations in larger regions introduces substantial visual ambiguity. To address these challenges, we propose RingMatch, a search-and-verification framework for wide-area cross-view localization. RingMatch first leverages predictive uncertainty to uncover plausible locations and progressively zooms into their surroundings to obtain increasingly fine-grained evidence, yielding a compact set of promising candidates. We then introduce the depth ring, a novel geometric representation that reveals subtle variations in the spatial layout around a location and serves as a view-shared spatial signature for an LVLM verifier to resolve residual ambiguity. To benchmark this setting, we construct VIGOR-Pro by composing VIGOR aerial tiles into contiguous regions with spatial extents of up to 400 m. Experiments show that RingMatch maintains strong localization performance as the aerial region expands, consistently outperforming representative end-to-end and retrieval-based methods.
Figures & tables
| Area | Method | ||||||
|---|---|---|---|---|---|---|---|
| Mean | Median | Mean | Median | Mean | Median | ||
| Same-area | End-to-End | ||||||
| HC-Net ( Wang et al., 2023 ) | 10.52 | 3.70 | 29.54 | 10.53 | 85.62 | 58.49 | |
| CCVPE ( Xia et al., 2024 ) | 9.63 | 2.11 | 14.07 | 2.64 | 27.90 | 3.48 | |
| FG 2 ( Xia and Alahi, 2025 ) | 9.76 | 4.63 | 18.38 | 8.14 | 38.41 | 17.00 | |
| Qwen3-VL-4B | 5.36 | 2.27 | 12.16 | 3.52 | 23.03 | 3.93 | |
| Verifier components | |||||||||
| Local patch | Depth ring | Search init. | ALL | VFY | ALL | VFY | ALL | VFY | |
| Search-only | – | – | – | 4.32 | 22.59 | 8.03 | 41.64 | 15.60 | 70.58 |
| w/ Verifier | – | – | 4.60 | 26.89 | 8.67 | 48.11 | 17.05 | 81.06 | |
| – | 4.26 | 21.67 | 7.36 | 34.77 | 13.89 | 58.17 | |||
| 4.02 | 17.59 | 6.57 | 26.69 | 12.36 | 47.12 | ||||
| Method | FT | ||
|---|---|---|---|
| Random | – | 50.00 | 50.00 |
| Ring-only | – | 67.29 | 69.42 |
| GPT-5.6 Terra | – | 56.93 | 59.47 |
| w/ depth ring | – | 67.58 (+10.65) | 66.21 (+6.74) |
| Gemini-3.7 Flash | – | 66.70 | 72.56 |
| w/ depth ring | – | 69.92 (+3.22) | 75.29 (+2.73) |
| Method | London | Tokyo | São Paulo | Cape Town | Overall | |||||
|---|---|---|---|---|---|---|---|---|---|---|
| Mean | Median | Mean | Median | Mean | Median | Mean | Median | Mean | Median | |
| FG 2 | 14.98 | 7.24 | 36.26 | 20.87 | 30.91 | 17.13 | 23.52 | 12.41 | 26.42 | 13.41 |
| Sample4Geo+FG 2 | 9.47 | 2.22 | 24.38 | 4.72 | 19.09 | 3.92 | 14.14 | 2.82 | 16.77 | 3.20 |
| RingMatch (Search-only) | 9.65 | 1.23 | 21.64 | 1.04 | 19.95 | 1.49 | 9.57 | 1.02 | 15.20 | 1.19 |
| RingMatch | 8.58 | 1.21 | 17.42 | 1.00 | 18.48 | 1.45 | 7.89 | 0.98 | 13.09 | 1.16 |
Appendix figures & tables16 assets
Supplementary material from the paper’s appendix.
Appendix
| City | GSD (m/pixel) | m | m | m |
|---|---|---|---|---|
| New York | 0.113248 | 108.72 | 217.44 | 398.63 |
| Seattle | 0.100817 | 96.78 | 193.57 | 354.88 |
| San Francisco | 0.118141 | 113.42 | 226.83 | 415.86 |
| Chicago | 0.111262 | 106.81 | 213.62 | 391.64 |
| Mean | 106.43 | 212.87 | 390.25 |
| Scale | Grid | Native | Mean side | Original | Original | Complete | Completion | Retained |
|---|---|---|---|---|---|---|---|---|
| resolution | (m) | panoramas | pairs | mosaics | rate (%) | panoramas | ||
| m | 106 | 105,214 | 420,856 | 417,375 | 99.17 | 105,214 | ||
| m | 213 | 105,214 | 420,856 | 400,740 | 95.22 | 104,098 | ||
| m | 390 | 105,214 | 420,856 | 372,532 | 88.52 | 101,053 |
| Configuration | Value | Configuration | Value |
|---|---|---|---|
| Initialization | Qwen3-VL-4B-Instruct | Optimizer | AdamW |
| Trainable | Language model | Batch size | 256 |
| Frozen | Vision, projector | Learning rate | |
| Training scales | m | Model input | px |
| Training epochs | 2 | LR schedule | Cosine |
| Warmup ratio | 0.1 |
| Initial scale | Search-region schedule (m) | Model-input size (px) |
|---|---|---|
| m | ||
| m | ||
| m |
| Configuration | Value | Configuration | Value |
| Model | |||
| Aerial patch | FFN width | 1,024 | |
| Azimuth samples | 360 | Depth classes | 80 |
| Metric depth range | m | Backbone | frozen DINOv2-B |
| DPT output width | 256 | Cross-attn. layers / heads | 4 / 8 |
| Training | |||
| Configuration | Value | Configuration | Value |
|---|---|---|---|
| Initialization | Search model | Training epochs | 2 |
| Trainable | Language model | Optimizer | AdamW |
| Frozen | Vision, projector | Learning rate | |
| Batch size | 256 | LR schedule | Cosine |
| Warmup ratio | 0.1 | Candidate shortlist | 2 |
| Candidate crop |
| City | GSD (m/pixel) | Side length (m) |
|---|---|---|
| London | 0.092883 | 178.33 |
| Tokyo | 0.121224 | 232.75 |
| São Paulo | 0.136834 | 262.72 |
| Cape Town | 0.123851 | 237.79 |
| Mean | 227.90 |
Cross-View Geo-Localization
Cross-view geo-localization matches ground, drone, or aerial images to maps or satellite views to estimate where they were captured.
See all 103 papers