Research map / 3D vision / Depth and stereo
Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator
Xiaolong Wang, Runsen Xu, Zhuofan Cui, Zeyu Wan, Yu Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use HC-Net instead of CCVPE* | VIGOR Same-Area, 0° noise · VIGOR Same-Area, 0° noise | mean localization error (m): 3.37 -> 2.65 | Improved |
| use HC-Net instead of CCVPE* | VIGOR Cross-Area, 0° noise · VIGOR Cross-Area, 0° noise | mean localization error (m): 4.96 -> 3.35 | Improved |
| use HC-Net instead of CCVPE | KITTI Same · KITTI Same | mean location error (m): 1.22 -> 0.80 | Improved |
| use HC-Net instead of CCVPE | KITTI Cross · KITTI Cross | mean location error (m): 9.16 -> 8.47 | Improved |
| use non-shared rather than shared backbone weights (ablation) | HC-Net · VIGOR Same-Area | mean localization error (m): 3.36 m -> 2.65 m | Improved |
| replace the deep homography estimator with SuperGlue and RANSAC (ablation) | HC-Net · VIGOR Same-Area | mean localization error (m): 2.65 m -> 13.06 m | Hurt |
| replace the deep homography estimator with LoFTR and RANSAC (ablation) | HC-Net · VIGOR Same-Area | mean localization error (m): 2.65 m -> 28.85 m | Hurt |
| use HC-Net instead of CCVPE | VIGOR · VIGOR | inference time: 33 ms -> 31 ms | Improved |
| use HC-Net instead of CCVPE | VIGOR · VIGOR | inference memory: 4730 MiB -> 1900 MiB | Improved |
Closest papers by meaning
- Where Am I Looking At? Joint Location and Orientation Estimation by Cross-View Matching (CVPR 2020 · similarity 0.89)
- Sector-Level Cross-View Geo-Localization with Implicit Orientation via Azimuthal Scanning (ECCV 2026 · similarity 0.88)
- From Coarse to Fine: A Matching and Alignment Framework for Unsupervised Cross-View Geo-Localization (AAAI 2025 · similarity 0.88)
- Aligning Geometric Spatial Layout in Cross-View Geo-Localization via Feature Recombination (AAAI 2024 · similarity 0.87)
- View From Above: Orthogonal-View aware Cross-view Localization (CVPR 2024 · similarity 0.87)
- Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
