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
Lokalisasi visual udara sangat penting untuk navigasi drone otonom di lingkungan perkotaan di mana sinyal GNSS sering degradasi. Model kota tanpa tekstur Level-of-Detail (LoD) menyediakan alternatif peta geometris untuk aset bertekstur. Metode berbasis siluet yang ada bergantung pada penyesuaian gambar-ruang, yang dapat meninggalkan pos kamera yang berbeda tidak dapat dibedakan dan mempromosikan posis yang salah ketika kesalahan segmentasi membingungkan skema bangunan. Kami menyajikan PlanarCityLoc, yang bergerak melampaui skema siluet dengan memanfaatkan geometri datar dari fasad bangunan dan atap. Setelah geometri-aware inisialisasi, kami mencocokkan patch plan dari gambar ke pesawat modelD dan menggunakan korelasi 3D-to-2D yang dihasilkan untuk memperbaiki posisinya dengan Perspective-n-Point (
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