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

• URL: http://arxiv.org/abs/2603.20697v1
• Date: Sat, 21 Mar 2026 07:47:33 GMT
• Title: Satellite-to-Street: Synthesizing Post-Disaster Views from Satellite Imagery via Generative Vision Models
• Abstract summary: We introduce two generative strategies to synthesize post-disaster street views from satellite imagery.<n>We benchmark these against general-purpose baselines (Pix2Pix, ControlNet) using a proposed Structure-Aware Evaluation Framework.<n>Experiments 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.
• Score: 10.715667868976054
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• DamageScope: Vision-Language Retrieval at Scale for Disaster Damage Assessment from Satellite Imagery [6.514592086157328]
  DamageScope is a retrieval-augmented framework that combines satellite imagery with Vision-Language Models (VLMs) and Large Language Models (LLMs)<n>Built on a Retrieval-Augmented Generation (RAG) framework, DamageScope extracts structured visual representations from satellite imagery to support interactive natural language queries for damage assessment.
  arXiv  Detail & Related papers  (2026-08-21T18:09:21Z)
• Optimizing Latent Representations for Robust Building Damage Assessment Onboard Earth Observation Satellites [0.0]
  We propose an original AI-based system that enables object-level building damage assessment (localization and damage classification) directly onboard satellites.<n>Available pre-disaster images are encoded on ground into compact latent representations, transmitted to the satellite, and compared on-board with newly acquired post-disaster observations.<n>We explore the design space through a systematic benchmark of onboard-compatible variants, analyzing the impact of siamese processing, cross-attention, latent-space compression, and robustness-oriented data augmentation.
  arXiv  Detail & Related papers  (2026-05-28T08:21:14Z)
• From Pixels to Semantics: A Multi-Stage AI Framework for Structural Damage Detection in Satellite Imagery [0.0]
  We propose a novel framework that integrates AI-based super-resolution, deep learning object detection, and Vision-Language Models (VLMs) for comprehensive post-disaster building damage assessment.<n>First, we enhance pre- and post-disaster satellite imagery using a Video Restoration Transformer (VRT) to upscale images from 1024x1024 to 4096x4096 resolution.<n>We employ CLIPScore for reference-free semantic alignment and introduce a multi-model VLM-as-a-Jury strategy to reduce individual model bias in safety-critical decision making.
  arXiv  Detail & Related papers  (2026-03-24T03:50:41Z)
• Satellite to Street : Disaster Impact Estimator [0.12938914787881173]
  The present work proposes a deep-learning framework that jointly processes pre- and post-disaster satellite images to obtain fine-grained pixel-level damage maps: Satellite-to-Street: Disaster Impact Estimator.<n>The model uses a modified dual-input U-Net architecture with enhanced feature fusion to capture both the local structural changes as well as the broader contextual cues.
  arXiv  Detail & Related papers  (2025-11-24T06:20:40Z)
• RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions [58.37558408672509]
  We propose a robust self-supervised training paradigm, consisting of two key steps: robust self-supervised scene correspondence learning and adverse weather distillation.<n>Experiments demonstrate the effectiveness and versatility of our proposed solution, which outperforms existing state-of-the-art self-supervised methods.
  arXiv  Detail & Related papers  (2025-09-23T15:41:40Z)
• REOBench: Benchmarking Robustness of Earth Observation Foundation Models [48.24281482353377]
  REOBench is the first comprehensive benchmark for evaluating the robustness of Earth observation foundation models.<n>We conduct a systematic evaluation of a broad range of models trained using masked image modeling, contrastive learning, and vision-language pre-training paradigms.<n>Results reveal that existing Earth observation foundation models experience significant performance degradation when exposed to input corruptions.
  arXiv  Detail & Related papers  (2025-05-22T15:34:50Z)
• Multiclass Post-Earthquake Building Assessment Integrating High-Resolution Optical and SAR Satellite Imagery, Ground Motion, and Soil Data with Transformers [0.0]
  We introduce a framework that combines high-resolution post-earthquake satellite imagery with building-specific metadata relevant to the seismic performance of the structure.<n>Our model achieves state-of-the-art performance in multiclass post-earthquake damage identification for buildings from the Turkey-Syria earthquake on February 6, 2023.
  arXiv  Detail & Related papers  (2024-12-05T23:19:51Z)
• Towards Evaluating the Robustness of Visual State Space Models [63.14954591606638]
  Vision State Space Models (VSSMs) have demonstrated remarkable performance in visual perception tasks. However, their robustness under natural and adversarial perturbations remains a critical concern. We present a comprehensive evaluation of VSSMs' robustness under various perturbation scenarios.
  arXiv  Detail & Related papers  (2024-06-13T17:59:44Z)
• OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images [59.51657161097337]
  OOD-CV-v2 is a benchmark dataset that includes out-of-distribution examples of 10 object categories in terms of pose, shape, texture, context and the weather conditions. In addition to this novel dataset, we contribute extensive experiments using popular baseline methods.
  arXiv  Detail & Related papers  (2023-04-17T20:39:25Z)
• Assessing out-of-domain generalization for robust building damage detection [78.6363825307044]
  Building damage detection can be automated by applying computer vision techniques to satellite imagery. Models must be robust to a shift in distribution between disaster imagery available for training and the images of the new event. We argue that future work should focus on the OOD regime instead.
  arXiv  Detail & Related papers  (2020-11-20T10:30:43Z)
• RescueNet: Joint Building Segmentation and Damage Assessment from Satellite Imagery [83.49145695899388]
  RescueNet is a unified model that can simultaneously segment buildings and assess the damage levels to individual buildings and can be trained end-to-end. RescueNet is tested on the large scale and diverse xBD dataset and achieves significantly better building segmentation and damage classification performance than previous methods.
  arXiv  Detail & Related papers  (2020-04-15T19:52:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.