Search papers, labs, and topics across Lattice.
This paper introduces the task of Text-to-OSM (T2O) global localization, which estimates 2-DoF positions from textual scene descriptions using OpenStreetMap data. To facilitate research in this area, the authors present TOL, a large-scale benchmark dataset containing 121K text queries paired with OSM map tiles across diverse urban environments. They also propose TOLoc, a coarse-to-fine localization framework that leverages direction-aware features and a dedicated alignment module to achieve state-of-the-art localization performance, outperforming existing methods by up to 9.93% at the 10m threshold.
Imagine pinpointing your location in a city using only a text description and OpenStreetMap data – this paper makes that a reality with a new benchmark and method that significantly outperforms existing localization techniques.
Natural language provides an intuitive way to express spatial intent in geospatial applications. While existing localization methods often rely on dense point cloud maps or high-resolution imagery, OpenStreetMap (OSM) offers a compact and freely available map representation that encodes rich semantic and structural information, making it well suited for large-scale localization. However, text-to-OSM (T2O) localization remains largely unexplored. In this paper, we formulate the T2O global localization task, which aims to estimate accurate 2 degree-of-freedom (DoF) positions in urban environments from textual scene descriptions without relying on geometric observations or GNSS-based initial location. To support the proposed task, we introduce TOL, a large-scale benchmark spanning multiple continents and diverse urban environments. TOL contains approximately 121K textual queries paired with OSM map tiles and covers about 316 km of road trajectories across Boston, Karlsruhe, and Singapore. We further propose TOLoc, a coarse-to-fine localization framework that explicitly models the semantics of surrounding objects and their directional information. In the coarse stage, direction-aware features are extracted from both textual descriptions and OSM tiles to construct global descriptors, which are used to retrieve candidate locations for the query. In the fine stage, the query text and top-1 retrieved tile are jointly processed, where a dedicated alignment module fuses textual descriptor and local map features to regress the 2-DoF pose. Experimental results demonstrate that TOLoc achieves strong localization performance, outperforming the best existing method by 6.53%, 9.93%, and 8.31% at 5m, 10m, and 25m thresholds, respectively, and shows strong generalization to unseen environments. Dataset, code and models will be publicly available at: https://github.com/WHU-USI3DV/TOL.
