Satellite-to-Street: Synthesizing Post-Disaster Views from Satellite Imagery via Generative Vision Models

TL;DR

This paper introduces methods to generate street-view images from satellite images after disasters, aiming to improve ground-level situational awareness using generative models and a comprehensive evaluation framework.

Contribution

It proposes two novel generative strategies for satellite-to-street view synthesis and a multi-tier evaluation protocol for assessing realism and semantic accuracy.

Findings

Diffusion models achieve high perceptual realism but may hallucinate details.

ControlNet attains the highest semantic accuracy at 0.71.

VLM and MoE models excel in textural plausibility but have semantic limitations.

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.