DECO is proposed, a DEpth-guided CO-visibility reasoning framework for low-altitude UAV visual localization that retains keypoints that are both visually distinctive and geometrically co-visible, improving feature matching and PnP-based pose estimation.
Abstract
Unmanned aerial vehicles (UAVs) increasingly require robust visual localization in GNSS-denied environments. A common solution estimates UAV poses by matching keypoints between UAV images and geo-tagged orthographic reference maps derived from satellite or aerial imagery, followed by Perspective-\(n\)-Point (PnP) pose solving. However, such reference maps mainly record top-down surfaces such as roofs and ground planes, while vertical structures such as facades and walls are often compressed or missing. Consequently, many visually distinctive keypoints in low-altitude UAV images have no valid counterparts in the reference map, leading to redundant matches and inaccurate pose estimation. To address this issue, we propose DECO, a DEpth-guided CO-visibility reasoning framework for low-altitude UAV visual localization. DECO uses monocular depth priors to infer local surface geometry and estimate co-visible regions between UAV images and the reference map. Based on this prior, a Geometry-Saliency Coupled Co-visibility Score is introduced to jointly consider geometric co-visibility and detector saliency for keypoint ranking. In this way, DECO retains keypoints that are both visually distinctive and geometrically co-visible, improving feature matching and PnP-based pose estimation. Extensive experiments demonstrate that DECO achieves superior localization performance and can be integrated with different depth models, feature detectors, and matchers. The source code will be available at https://github.com/UAV-AVL/DECO.
Abstract. Navigating Unmanned Aerial Vehicles (UAVs) in Global Navigation Satellite System (GNSS)-denied environments requires reliable autonomous localization techniques. This study proposes a vision-based localization framework utilizing satellite true orthophotos and Digital Surface Models (DSMs) as absolute geospatial references. The algorithmic pipeline integrates deep learning architectures—specifically SuperPoint and LightGlue—to establish robust image-to-map feature correspondences. The matched correspondences are used to estimate camera exterior orientation parameters through collinearity-based spatial resection with an Iteratively Reweighted Least Squares (IRLS) approach. To validate the proposed methodology, a multi-altitude dataset (100–250 m) was acquired across structurally diverse terrains, including dense building, high vegetation, and bare ground areas. Experimental evaluations demonstrate that the framework achieves meter-level absolute positioning accuracy and stable pose estimation. Analyses further reveal that matching robustness and localization success rates depend heavily on terrain texture and flight altitude; geometrically structured urban scenes at moderate-to-high altitudes consistently yield reliable correspondences, whereas low-texture environments and lower flight altitudes present persistent challenges for continuous visual tracking.
Tai-Cyuan Wang, Lai-Han Tsou, J. Jhan et al.· The International Archives o...· 0 citations
Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, differences in acquisition time and imaging platform between UAV and reference imagery introduce substantial cross-domain appearance and viewpoint shifts, challenging robust six-degree-of-freedom (6-DoF) pose estimation. To mitigate these shifts, we render UAV-viewpoint references from Google 3D Tiles across locations, altitudes, and orientations. A two-stage strategy adapts SALAD with pose-near positives and geographically distant hard negatives; local geometric consistency then re-ranks the Top-K candidates. We further propose Retrieval-In-Matching (RIM), which freezes the adapted DINOv2-B retriever and distills a local-descriptor decoder from its token field and a shallow VGG19 detail stream. One query-side DINOv2-B backbone forward therefore supports both SALAD retrieval and local description, eliminating a second foundation-model backbone while preserving the retrieval descriptors by construction. We evaluate RIM zero-shot on the reconstructed EPFL Urbanscape and self-collected Chang'an Park datasets, both geographically disjoint from the training data. RIM outperforms ten retrieval baselines. Under the full 3D distance metric at 25/50 m, it improves Recall@1 over SALAD by 8.55/13.77 percentage points on EPFL and 4.45/8.94 points on Park. At Top-K=5, the measured online query path through retrieval, candidate matching, and robust geometric verification takes 90.8 ms: 1.2 times faster than the strongest separate sparse-matching baseline and over 30 times faster than RoMa, while maintaining comparable re-ranking accuracy. These results demonstrate an efficient UAV global visual localization pipeline under unreliable satellite navigation. The source code is available at https://github.com/curious-energy/RIM.
Xin Li, Si-Yuan Duan, Shang Wang et al.· Knowledge-Based Systems· 1 citation
Accurate absolute localization is essential to uncrewed aerial vehicles (UAVs) operating in low-altitude environments. Global navigation satellite system (GNSS) signals are weak and susceptible to interference, making them unreliable in the case of absolute positioning. Absolute visual localization (AVL), which matches onboard images with geo-referenced satellite maps, provides a viable alternative in GNSS-denied scenarios. However, many existing approaches rely on an assumption of similarity transformation between images to be aligned, which is often violated by nonzero horizontal angles in practice, leading to localization bias and fragility to appearance variations. This article proposes a visual alignment localization method that estimates the full homography between UAV and satellite images and fuses it with incremental motion observations. By jointly modeling orientation and position, the method reduces geometric bias and improves localization robustness under nonnadir viewing conditions. Experiments on real-world UAV datasets demonstrate improved localization accuracy and stability, particularly in flight sequences with nonzero horizontal attitude angles. The source code for our method is available at https://github.com/lizhipro/KF-HomoVAL
Ban Li, Jianghui Geng, Hongping Zhang et al.· IEEE Transactions on Geoscie...· 0 citations
Abstract. Reliable visual localization is essential for long-range VTOL UAV mapping in GNSS-degraded environments. This paper presents a quantitative evaluation framework for monocular ORB-SLAM3 using a 66.48 km multi-altitude UAV mission and aerial-triangulation-derived camera poses as reference data. The workflow associates SLAM and reference trajectories by image key, applies Sim(3)-based metric alignment, corrects coordinate-axis inconsistency, and refines attitude by a global rotation offset, enabling full-mission and segment-level comparison in a common metric frame. The evaluation covers four altitude segments, namely 100, 150, 200, and 250 m AGL, under three protocols: No-Loop (NL), With-Loop Global Slice (GS), and With-Loop Local Re-Sim(3) (LR). For the full mission, the proposed alignment achieves a 3D position RMSE of 7.41 m over 5330 matched frames and substantially reduces the geometric deformation observed in the S+T baseline. Segment-level results show a strong altitude dependency in the isolated NL runs, with 3D RMSE decreasing from 22.95 m at 100 m to 5.49 m at 250 m. Among the three protocols, LR consistently yields the best segment-level position accuracy, reaching 4.00, 8.26, 3.94, and 3.92 m at 100, 150, 200, and 250 m, respectively. Long-range analysis further shows that the trajectory remains globally bounded, while cumulative 3D endpoint drift increases from 0.35 m at 50 m to 10.66 m at 25.6 km. These results indicate that ORB-SLAM3 can support large-scale trajectory estimation for UAV mapping, but its evaluated quality depends strongly on alignment, segmentation, and evaluation strategy.
Ming-Jyun Yang, J. Jhan, Runmeng Tang· The International Archives o...· 1 citation
Monocular depth estimation is a fundamental prerequisite for 3D reconstruction and autonomous navigation in Unmanned Aerial Vehicles (UAVs). In practical deployments, UAVs operate under highly dynamic camera poses characterized by continuous variations in height, pitch, roll, and field of view (FOV). Existing monocular depth estimation methods frequently fail to generalize across such diverse perspectives and the expansive scale of depth distributions inherent in aerial scenes. To address these challenges, we establish a quantitative representation of UAV viewing angles through rigorous theoretical analysis, deriving the geometric correspondence between viewing angles and view distances using the ground plane as a reference for observation. Building upon this, we propose Depth Estimation for Any Perspectives Model (DAPM), representing the first monocular framework specifically designed for UAV aerial imagery to jointly estimate camera pose and depth under continuously varying viewpoints. Specifically, we introduce an Ideal Ground Depth (IGD) module that leverages the derived geometric relationships between UAV perspectives and view distances to implement dense camera-pose supervision and enhance depth features. And we further develop a coarse-to-fine Progressive Quantization Bins (PQB) module. By incorporating progressive supervision and hierarchical quantization bins, the PQB module enables robust estimation in complex UAV aerial imagery. To evaluate the proposed framework, we present the UAV Any Perspectives Depth (UAPD) dataset, featuring comprehensive and continuous distributions of pose parameters. Experimental results on UAPD demonstrate that DAPM achieves state-of-the-art performance across both depth and camera-pose estimation metrics. The source code and datasets are available at: https://github.com/ThisIsLT/DAPM.
Online incremental orthophoto generation with multiple unmanned aerial vehicles (UAVs) remains challenging, as it requires accurate, efficient, and scalable mapping from distributed aerial observations. In this paper, we present a centralized GNSS-assisted multi-UAV 3D Gaussian Splatting SLAM framework for online incremental orthophoto mapping. Each UAV independently performs visual odometry to build local submaps, which are first aligned into a unified global coordinate system using GNSS constraints and further refined via inter-agent visual loop closures for improved cross-agent consistency. To enable scalable and high-quality mapping, we introduce two complementary Gaussian map maintenance modules: plane-guided grid-based collaborative densification, which improves mapping quality and accelerates convergence under multi-UAV conditions, and visibility-aware adaptive pruning, which effectively controls redundancy and memory usage. These components allow efficient joint optimization within a unified Gaussian representation. Experiments on multiple aerial datasets using video-derived image frames captured by consumer-grade UAV cameras demonstrate that the proposed system provides a favorable trade-off between geo-consistency, visual fidelity, and efficiency compared with existing methods. Quantitatively, the proposed method achieves a GCP RMSE of 2.32 m, completes multi-UAV orthophoto generation within 3.3–5.5 min, and reduces the total mapping time by approximately 35–55% compared with the corresponding single-UAV setting, while supporting online tracking and incremental orthophoto updates with bounded latency and memory consumption.
