Cross3R performs feed-forward 3D reconstruction and 6-DoF pose estimation from any combination of satellite, UAV, and ground images, outperforming baselines on a new 278K-image tri-view dataset.
Exploring the best way for UAV visual localization under Low-altitude Multi-view Observation Condition: a Benchmark
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Absolute Visual Localization (AVL) enables an Unmanned Aerial Vehicle (UAV) to determine its position in GNSS-denied environments by establishing geometric relationships between UAV images and geo-tagged reference maps. While many previous works have achieved AVL with image retrieval and matching techniques, research in low-altitude multi-view scenarios still remains limited. Low-altitude multi-view conditions present greater challenges due to extreme viewpoint changes. To investigate effective UAV AVL approaches under such conditions, we present this benchmark. Firstly, a large-scale low-altitude multi-view dataset called AnyVisLoc was constructed. This dataset includes 18,000 images captured at multiple scenes and altitudes, along with 2.5D reference maps containing aerial photogrammetry maps and historical satellite maps. Secondly, a unified framework was proposed to integrate the state-of-the-art AVL approaches and comprehensively test their performance. The best combined method was chosen as the baseline, and the key factors influencing localization accuracy are thoroughly analyzed based on it. This baseline achieved a 74.1% localization accuracy within 5 m under low-altitude, multi-view conditions. In addition, a novel retrieval metric called PDM@K was introduced to better align with the characteristics of the UAV AVL task. Overall, this benchmark revealed the challenges of low-altitude, multi-view UAV AVL and provided valuable guidance for future research. The dataset and code are available at https://github.com/UAV-AVL/Benchmark
citation-role summary
background 1
dataset 1
citation-polarity summary
fields
cs.CV 4years
2026 4representative citing papers
Bearing-UAV predicts UAV location and heading directly from cross-view image features, yielding lower localization error than tile-matching methods across diverse terrains on a new multi-city benchmark.
SkyPart achieves state-of-the-art single-pass cross-view geo-localization on SUES-200, University-1652, and DenseUAV by using prototype-based part discovery, altitude-conditioned modulation, and Kendall-weighted loss, with widening gains under weather corruptions.
SCC-Loc achieves 9.37 m mean localization error for UAV thermal images against satellite references, a 7.6-fold gain inside the 5 m threshold over prior methods, using a shared DINOv2 backbone plus three new semantic-consensus modules.
citing papers explorer
-
Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
Cross3R performs feed-forward 3D reconstruction and 6-DoF pose estimation from any combination of satellite, UAV, and ground images, outperforming baselines on a new 278K-image tri-view dataset.
-
Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation
Bearing-UAV predicts UAV location and heading directly from cross-view image features, yielding lower localization error than tile-matching methods across diverse terrains on a new multi-city benchmark.
-
Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
SkyPart achieves state-of-the-art single-pass cross-view geo-localization on SUES-200, University-1652, and DenseUAV by using prototype-based part discovery, altitude-conditioned modulation, and Kendall-weighted loss, with widening gains under weather corruptions.
-
SCC-Loc: A Unified Semantic Cascade Consensus Framework for UAV Thermal Geo-Localization
SCC-Loc achieves 9.37 m mean localization error for UAV thermal images against satellite references, a 7.6-fold gain inside the 5 m threshold over prior methods, using a shared DINOv2 backbone plus three new semantic-consensus modules.