Scholarlink

<p>Street view imagery has become an essential source for geospatial data collection and urban analytics, enabling the extraction of valuable insights that support informed decision-making. However, synthesizing street-view images from corresponding satellite imagery presents significant challenges due to substantial differences in appearance and viewing perspective between these two domains. This paper presents a hybrid framework that integrates diffusion-based models and conditional generative adversarial networks to generate geographically consistent street-view images from satellite imagery. Our approach uses a multi-stage training strategy that incorporates Stable Diffusion as the core component within a dual-branch architecture. To enhance the framework’s capabilities, we integrate a conditional Generative Adversarial Network (GAN) that enables the generation of geographically consistent panoramic street views. Furthermore, we implement a fusion strategy that leverages the strengths of both models to create robust representations, thereby improving the geometric consistency and visual quality of the generated street-view images. The proposed framework is evaluated on the challenging Cross-View USA (CVUSA) dataset, a standard benchmark for cross-view image synthesis. Experimental results demonstrate that our hybrid approach achieves an 11.75% improvement in PSNR over the diffusion-only CrossViewDiff method (13.41 vs. 12.00), indicating superior pixel-level accuracy. Compared to the recent GAN-based Sat2Density approach, our framework achieves improvements of 2.18% in SSIM (0.3464 vs. 0.339) and 2.68% in FID (40.32 vs. 41.43), demonstrating enhanced structural similarity and improved distribution matching. The framework successfully generates realistic and geometrically consistent street-view images while preserving fine-grained local details, including street markings, secondary roads, and atmospheric elements such as clouds.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

From satellite to street: a hybrid framework integrating stable diffusion and PanoGAN for consistent cross–view synthesis

  • 期刊论文

  • 发表日期：

    2026年5月2日

查看全文
  • Khawlah Bajbaa,
  • Abbas Anwar,
  • Muhammad Saqib,
  • Hafeez Anwar,
  • Nabin Sharma,
  • Muhammad Usman

摘要

Street view imagery has become an essential source for geospatial data collection and urban analytics, enabling the extraction of valuable insights that support informed decision-making. However, synthesizing street-view images from corresponding satellite imagery presents significant challenges due to substantial differences in appearance and viewing perspective between these two domains. This paper presents a hybrid framework that integrates diffusion-based models and conditional generative adversarial networks to generate geographically consistent street-view images from satellite imagery. Our approach uses a multi-stage training strategy that incorporates Stable Diffusion as the core component within a dual-branch architecture. To enhance the framework’s capabilities, we integrate a conditional Generative Adversarial Network (GAN) that enables the generation of geographically consistent panoramic street views. Furthermore, we implement a fusion strategy that leverages the strengths of both models to create robust representations, thereby improving the geometric consistency and visual quality of the generated street-view images. The proposed framework is evaluated on the challenging Cross-View USA (CVUSA) dataset, a standard benchmark for cross-view image synthesis. Experimental results demonstrate that our hybrid approach achieves an 11.75% improvement in PSNR over the diffusion-only CrossViewDiff method (13.41 vs. 12.00), indicating superior pixel-level accuracy. Compared to the recent GAN-based Sat2Density approach, our framework achieves improvements of 2.18% in SSIM (0.3464 vs. 0.339) and 2.68% in FID (40.32 vs. 41.43), demonstrating enhanced structural similarity and improved distribution matching. The framework successfully generates realistic and geometrically consistent street-view images while preserving fine-grained local details, including street markings, secondary roads, and atmospheric elements such as clouds.