# Satellite-to-Street: Synthesizing Post-Disaster Views from Satellite Imagery via Generative Vision Models Source: [Satellite-to-Street: Synthesizing Post-Disaster Views from Satellite Imagery via Generative Vision Models]() Collection index: [llms.txt]() Data updated: 2026-03-25T05:00:04.214Z Authors: Yifan Yang, Lei Zou, Wendy Jepson Published: 2026-03-21T07:47:33.000Z ## Abstract In the immediate aftermath of natural disasters, rapid situational awareness is critical. Traditionally, satellite observations are widely used to estimate damage extent. However, they lack the ground-level perspective essential for characterizing specific structural failures and impacts. Meanwhile, ground-level data (e.g., street-view imagery) remains largely inaccessible during time-sensitive events. This study investigates Satellite-to-Street View Synthesis to bridge this data gap. We introduce two generative strategies to synthesize post-disaster street views from satellite imagery: a Vision-Language Model (VLM)-guided approach and a damage-sensitive Mixture-of-Experts (MoE) method. We benchmark these against general-purpose baselines (Pix2Pix, ControlNet) using a proposed Structure-Aware Evaluation Framework. This multi-tier protocol integrates (1) pixel-level quality assessment, (2) ResNet-based semantic consistency verification, and (3) a novel VLM-as-a-Judge for perceptual alignment. Experiments on 300 disaster scenarios reveal a critical realism--fidelity trade-off: while diffusion-based approaches (e.g., ControlNet) achieve high perceptual realism, they often hallucinate structural details. Quantitative results show that standard ControlNet achieves the highest semantic accuracy, 0.71, whereas VLM-enhanced and MoE models excel in textural plausibility but struggle with semantic clarity. This work establishes a baseline for trustworthy cross-view synthesis, emphasizing that visually realistic generations may still fail to preserve critical structural information required for reliable disaster assessment. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Satellite-to-Street-View Synthesis on Satellite-to-Street-View Disaster Dataset](): Satellite-to-Street-View Synthesis; Satellite-to-Street-View Disaster Dataset; Structural Fidelity: 1.88. - [Disaster Severity Classification on Synthesized Post-Disaster Street-View Images (test)](): Disaster Severity Classification; Synthesized Post-Disaster Street-View Images (test); Accuracy: 43. - [Satellite-to-Street-View Image Synthesis on Hurricane Ian dataset](): Satellite-to-Street-View Image Synthesis; Hurricane Ian dataset; SSIM: 29.1. ## Original sources and implementation [Original paper]() [PDF]()