Oussema Dhaouadi, Shao Jie Hu-Chen, Jakob Gollreiter, Samir Jusufi, Nikolas Rieger, Caroline Wendlandt, Christian Wender, Jingfeng Mao, Guangming Wang, Zuria Bauer, Marc Pollefeys, Daniel Cremers, Olaf Wysocki · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.26729 · cited by 0 works (OpenAlex) · open-access PDF
La localización visual aérea es crucial para la navegación de drones autónoma en entornos urbanos donde las señales GNSS a menudo se degradan. Los modelos de ciudades sin textura de nivel de detalle (LoD) proporcionan una alternativa geométrica a los activos texturados. Los métodos existentes basados en silueta se basan en el alineamiento de imagen-espacio, que puede dejar diferentes posiciones de la cámara indistinguibles y favorecer posiciones incorrectas cuando los errores de segmentación distorsionan los esquemas de la construcción. Presentamos PlanarCityLoc, que se mueve más allá de la superposición de la silueta aprovechando la geometría plana de las fachadas y techos de la construcción. Después de la inicialización consciente de la geometría, ajustamos los par
Machine translation (Meta M2M100); the English original follows.
Aerial visual localization is crucial for autonomous drone navigation in urban environments where GNSS signals are often degraded. Lightweight textureless Level-of-Detail (LoD) city models provide a geometric map alternative to textured assets. Existing silhouette-based methods rely on image-space alignment, which can leave different camera poses indistinguishable and favor incorrect poses when segmentation errors distort the building outlines. We present PlanarCityLoc, which moves beyond silhouette overlap by leveraging the planar geometry of building facades and roofs. Following geometry-aware initialization, we match image-side planar patches to LoD model planes and use the resulting 3D-to-2D correspondences to refine pose with Perspective-n-Point (PnP). The framework uses off-the-shelf geometry and segmentation models without dataset-specific training or fine-tuning. Experiments on UAVD4L-LoDv2 and Swiss-EPFLv2 achieve state-of-the-art localization recall among the evaluated off-the-shelf LoD-based methods. By grounding image-space alignment in 3D planes, PlanarCityLoc enables more accurate aerial localization with lightweight, textureless city maps.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Silhouette, Computer vision, Artificial intelligence, Segmentation, Computer science, Drone
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26729, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange