3dSAGER: Geospatial Entity Resolution over 3D Objects (Technical Report)
Bar Genossar, Sagi Dalyot, Roee Shraga, Avigdor Gal
TL;DR
3dSAGER addresses geospatial entity resolution for 3D objects without relying on coordinates or metadata by learning a geometry-driven representation from polygon meshes. It introduces a two-stage pipeline: (i) coordinate-agnostic featurization that yields property vectors and pairwise ratio features, and (ii) an end-to-end matcher trained on these features, complemented by BKAFI, a blocking method that uses feature-importance-derived keys to efficiently generate high-recall candidate sets. The authors contribute a new large-scale benchmark (The Hague) plus a post-disaster dataset to validate performance, showing substantial accuracy and efficiency gains over image-based baselines and ensuring scalability for urban planning and disaster response. The work demonstrates robust performance under contamination and transfer scenarios, underscoring the practicality of geometry-focused 3D ER in real-world, cross-source, and resource-constrained settings.
Abstract
Urban environments are continuously mapped and modeled by various data collection platforms, including satellites, unmanned aerial vehicles and street cameras. The growing availability of 3D geospatial data from multiple modalities has introduced new opportunities and challenges for integrating spatial knowledge at scale, particularly in high-impact domains such as urban planning and rapid disaster management. Geospatial entity resolution is the task of identifying matching spatial objects across different datasets, often collected independently under varying conditions. Existing approaches typically rely on spatial proximity, textual metadata, or external identifiers to determine correspondence. While useful, these signals are often unavailable, unreliable, or misaligned, especially in cross-source scenarios. To address these limitations, we shift the focus to the intrinsic geometry of 3D spatial objects and present 3dSAGER (3D Spatial-Aware Geospatial Entity Resolution), an end-to-end pipeline for geospatial entity resolution over 3D objects. 3dSAGER introduces a novel, spatial-reference-independent featurization mechanism that captures intricate geometric characteristics of matching pairs, enabling robust comparison even across datasets with incompatible coordinate systems where traditional spatial methods fail. As a key component of 3dSAGER, we also propose a new lightweight and interpretable blocking method, BKAFI, that leverages a trained model to efficiently generate high-recall candidate sets. We validate 3dSAGER through extensive experiments on real-world urban datasets, demonstrating significant gains in both accuracy and efficiency over strong baselines. Our empirical study further dissects the contributions of each component, providing insights into their impact and the overall design choices.