AI Paper Atlas

Research map / Benchmarks / CVUSA

CVUSA leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CVUSA. Best R@1: 99.67 (Ours, CVPR 2020).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CVUSA · R@1

15 papers, each with its best reported number for its own method; higher is better.

#R@1 ↑MethodPaperTopic
199.67Ours
VGG16
Where Am I Looking At? Joint Location and Orientation Estimation by Cross-View Matching
CVPR 2020 · Table: Comparison with existin
Depth and stereo
299.61OursAccurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching
TPAMI 2022 · Table 1
Depth and stereo
399.3UA-Geo
DINOv3 ViT-B
Must All Negatives Be Pushed Away Equally? Uncertainty-Aware Cross-View Geo-Localization via Normal Inverse Gamma Distribution
ICML 2026 · Table 1
Recognition and long-tail
499.29Ours (consensus mining)Warp-free Cross-view Geo-localization via Feature-space Consensus Mining
ECCV 2026 · Table 1
Depth and stereo
599.14GeoBridge
CLIP-L/14
GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization
CVPR 2026 · Table 4
Cross-modal learning
698.85CLGT (γ=0.5)
EP-BEV
CVGL: Causal Learning and Geometric Topology
NeurIPS 2025 · Table: Comparisons with state-
Recognition and long-tail
798.83Geo2
VGGT + Sample4Geo ConvNeXt
Geo2: Geometry-Guided Cross-view Geo-Localization and Image Synthesis
CVPR 2026 · Table 3
3D generation
898.71Panorama-BEV Co-Retrieval (Ours)
ConvNeXt-B
Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network
ECCV 2024 · Table 2
Depth and stereo
998.68Sample4Geo
ConvNeXt-B
Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation
ICCV 2023 · Table 1
Depth and stereo
1097.06Ours (FRGeo)
ConvNeXt-T
Aligning Geometric Spatial Layout in Cross-View Geo-Localization via Feature Recombination
AAAI 2024 · Table 1
3D generation
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.