A Diffusion-Based Framework for Terrain-Aware Remote Sensing Image Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908322542649344 |
|---|---|
| author | Yu, Zhenyu Idris, Mohd Yamani Inda Wang, Pei |
| author_facet | Yu, Zhenyu Idris, Mohd Yamani Inda Wang, Pei |
| contents | Remote sensing imagery is essential for environmental monitoring, agricultural management, and disaster response. However, data loss due to cloud cover, sensor failures, or incomplete acquisition-especially in high-resolution and high-frequency tasks-severely limits satellite imagery's effectiveness. Traditional interpolation methods struggle with large missing areas and complex structures. Remote sensing imagery consists of multiple bands, each with distinct meanings, and ensuring consistency across bands is critical to avoid anomalies in the combined images. This paper proposes SatelliteMaker, a diffusion-based method that reconstructs missing data across varying levels of data loss while maintaining spatial, spectral, and temporal consistency. We also propose Digital Elevation Model (DEM) as a conditioning input and use tailored prompts to generate realistic images, making diffusion models applicable to quantitative remote sensing tasks. Additionally, we propose a VGG-Adapter module based on Distribution Loss, which reduces distribution discrepancy and ensures style consistency. Extensive experiments show that SatelliteMaker achieves state-of-the-art performance across multiple tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_12112 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Diffusion-Based Framework for Terrain-Aware Remote Sensing Image Reconstruction Yu, Zhenyu Idris, Mohd Yamani Inda Wang, Pei Computer Vision and Pattern Recognition Image and Video Processing Remote sensing imagery is essential for environmental monitoring, agricultural management, and disaster response. However, data loss due to cloud cover, sensor failures, or incomplete acquisition-especially in high-resolution and high-frequency tasks-severely limits satellite imagery's effectiveness. Traditional interpolation methods struggle with large missing areas and complex structures. Remote sensing imagery consists of multiple bands, each with distinct meanings, and ensuring consistency across bands is critical to avoid anomalies in the combined images. This paper proposes SatelliteMaker, a diffusion-based method that reconstructs missing data across varying levels of data loss while maintaining spatial, spectral, and temporal consistency. We also propose Digital Elevation Model (DEM) as a conditioning input and use tailored prompts to generate realistic images, making diffusion models applicable to quantitative remote sensing tasks. Additionally, we propose a VGG-Adapter module based on Distribution Loss, which reduces distribution discrepancy and ensures style consistency. Extensive experiments show that SatelliteMaker achieves state-of-the-art performance across multiple tasks. |
| title | A Diffusion-Based Framework for Terrain-Aware Remote Sensing Image Reconstruction |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2504.12112 |