Building aware satellite method improves urban 3d maps accuracy
Agentic Building-Aware Satellite Gaussian Splatting for Auditable Urban DSM Reconstruction
Computer Vision and Pattern Recognition
Summary
Making detailed 3D maps of cities from satellite images helps with disaster response and city planning, but most methods focus on making the whole scene look good instead of accurately capturing buildings. The authors developed a new approach that uses building outlines detected from images to focus the mapping on buildings, improving the measurement accuracy for these important structures. Their system also records how it chooses its mapping settings to make the process auditable and trustworthy.
What this means in practice
- •For disaster response teams: Create more accurate 3D urban maps from satellites that emphasize buildings to improve damage assessment after disasters.
- •For urban planning departments: Generate detailed and auditable 3D building models from satellite data to support city monitoring and development decisions.
Authors
Wentao Sun, Zhengsen Xu, Yiping Chen, John S. Zelek, Jonathan Li
Abstract
Urban-scale 3D reconstruction from satellite imagery supports disaster response, city monitoring, and geospatial digital twins, yet neural rendering methods typically optimize average visual fidelity rather than the structures that analysts inspect first: buildings. We present an agentic building-aware satellite Gaussian Splatting workflow that uses Segment Anything-derived building masks as semantic priors and an Agentic Reconstruction Controller to select, verify, and record DSM reconstruction policies. On the DFC2019 JAX\_004 scene, building-aware weighting reduces building-region DSM MAE from 0.844 m to 0.806 m, showing that semantic priors can shift reconstruction capacity toward analyst-critical regions. A staged schedule provides a balanced operating point, improving full-scene MAE from 1.362 m to 1.349 m while retaining a building gain. Across four JAX scenes, the Agent selects validated policies for both general DSM and building-focused DSM objectives, and produces building-inventory metadata and per-scene decision records. The system combines semantic priors, policy selection, region-specific DSM metrics, and DSM-derived GIS surface products for auditable urban 3D analysis.