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

Yifan Yang; Lei Zou; Wendy Jepson

cs.CVMar 21, 2026

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

Authors: Yifan Yang, Lei Zou, Wendy Jepson

Organizations: Department of Geography, Texas A&M University, College Station, TX, USA

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.

Figures & tables

Fig. 1: Overview of the proposed structure-aware evaluation framework and generative benchmarks. We systematically evaluate four paradigms: (A) Pix2Pix (baseline), (B) Stable Diffusion with ControlNet (baseline), (C) VLM-guided synthesis (Ours), and (D) Disaster-MoE framework (Ours). The generated street-view images are assessed using a multi-tier protocol: pixel-level metrics, ResNet-based semantic consistency, and VLM-driven perceptual quality.

Fig. 2: Qualitative comparison of satellite-to-street-view synthesis results across different disaster severity levels. Columns correspond to Pix2Pix, Stable Diffusion 1.5 with ControlNet, Stable Diffusion 1.5 with ControlNet and VLM-guidance, the Mixture-of-Experts (MoE) model, and ground truth.

Fig. 3: Confusion matrices of disaster severity classification. Pix2Pix collapses to the ‘Mild’ class, while ControlNet shows strong separability. VLM-Guided and MoE models exhibit increased confusion between moderate and severe levels, reflecting the complexity of generated damage patterns.

Method	SSIM $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$	FID $\downarrow$
Pix2Pix	0.586	15.31	0.549	150.83
SD1.5 + ControlNet	0.314	9.81	0.602	74.33
SD1.5 + ControlNet + VLM	0.291	9.73	0.604	82.19
Disaster-MoE	0.222	8.45	0.688	134.52

TABLE I: Quantitative Comparison of Perceptual Image Quality Metrics

Method	Acc. $\uparrow$	F1 $\uparrow$	Mild $\uparrow$	Mod. $\uparrow$	Sev. $\uparrow$
Ground Truth	0.73	0.74	0.77	0.76	0.66
Pix2Pix	0.34	0.17	1.00	0.01	0.00
SD1.5 + ControlNet	0.72	0.71	0.91	0.40	0.86
SD1.5 + ControlNet + VLM	0.43	0.43	0.40	0.39	0.50
Disaster-MoE	0.43	0.44	0.41	0.47	0.42

TABLE II: Classification Accuracy for Disaster Severity Consistency

Method	Struct. $\uparrow$	Damage $\uparrow$	Realism $\uparrow$
Pix2Pix	1.26	1.08	1.00
SD1.5 + ControlNet	1.43	1.68	2.11
SD1.5 + ControlNet + VLM	1.88	2.04	2.08
Disaster-MoE	1.61	1.79	2.11

TABLE III: Semantic and Perceptual Evaluation by LLM-as-a-Judge

Image Generation

Image generation studies models that create or edit images from text, examples, layouts, and other structured controls.

See all 463 papers

GroundControl: Satellite-Conditioned Multi-View Diffusion for Reconstruction-Free Novel View Synthesis
Oct 27, 2026Akshay Krishnan, Matias Turkulainen, Jamie Wynn +7Novel View Synthesis Multi-View Diffusion Models
Niantic Spatial · Georgia Institute of Technology · Aalto University
DamageArbiter: A Multimodal Arbitration Framework for Disaster Damage Assessment from Street-View Imagery
Mar 16, 2026Yifan Yang, Lei Zou, Wenjing Gong +6Disaster Damage Assessment Multimodal Classification
Department of Geography, Texas A&M University, College Station, USA · Department of Landscape Architecture & Urban Planning, Texas A&M University, College Station, USA · Department of Industrial and Systems Engineering, University of Florida, Gainesville, USA +2
Generating Satellite Imagery Data for Wildfire Detection through Mask-Conditioned Generative AI
Apr 2, 2026Valeria Martin, K. Brent Venable, Derek MorganSynthetic Data Augmentation Conditional Image Generation
Department of Intelligent Systems and Robotics, University of West Florida, Pensacola, FL, USA · IHMC, Pensacola, FL, USA

Oct 27, 2026J/K move · Enter open · S save

GroundControl: Satellite-Conditioned Multi-View Diffusion for Reconstruction-Free Novel View Synthesis

Akshay Krishnan, Matias Turkulainen, Jamie Wynn, Zawar Qureshi+6

Niantic Spatial · Georgia Institute of Technology · Aalto University

Novel View Synthesis Multi-View Diffusion Models

Open paper AskPDF arXiv

Multi-view or video diffusion models have recently emerged as state-of-the-art approaches for novel-view synthesis from sparse image collections. While they can produce high quality images, they tend to hallucinate unrealistic spatial layouts when synthesizing views outside the input views (scene extrapolation). We propose to address this challenge for outdoor scenes by using satellite images as an additional information source to condition the multi-view generative model. We introduce a new satellite-conditioned multi-view diffusion model that combines conditioning from a satellite image and street-level input images when generating novel-views. Our cross-attention based conditioning allows us to retain pretrained multi-view diffusion priors to generate seamless, realistic, novel views from a handful of source views, while also adhering to the scene layout as seen from satellite images. Our model does not use 3D scene reconstruction, and only relies on posed street and satellite views. Our experiments on outdoor datasets show that our model is better than both satellite-conditioned or street-view conditioned baselines on novel-view synthesis, especially on challenging cases where target views have very little overlap with source views. Project page: https://nianticspatial.github.io/groundcontrol

Abstract

Image Generation

Explore similar work

GroundControl: Satellite-Conditioned Multi-View Diffusion for Reconstruction-Free Novel View Synthesis

DamageArbiter: A Multimodal Arbitration Framework for Disaster Damage Assessment from Street-View Imagery

Generating Satellite Imagery Data for Wildfire Detection through Mask-Conditioned Generative AI