From Spaceborne to Airborne: SAR Image Synthesis Using Foundation Models for Multi-Scale Adaptation
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_ | 1866913831204159488 |
|---|---|
| author | Debuysere, Solene Trouve, Nicolas Letheule, Nathan Leveque, Olivier Colin, Elise |
| author_facet | Debuysere, Solene Trouve, Nicolas Letheule, Nathan Leveque, Olivier Colin, Elise |
| contents | The availability of Synthetic Aperture Radar (SAR) satellite imagery has increased considerably in recent years, with datasets commercially available. However, the acquisition of high-resolution SAR images in airborne configurations, remains costly and limited. Thus, the lack of open source, well-labeled, or easily exploitable SAR text-image datasets is a barrier to the use of existing foundation models in remote sensing applications. In this context, synthetic image generation is a promising solution to augment this scarce data, enabling a broader range of applications. Leveraging over 15 years of ONERA's extensive archival airborn data from acquisition campaigns, we created a comprehensive training dataset of 110 thousands SAR images to exploit a 3.5 billion parameters pre-trained latent diffusion model \cite{Baqu2019SethiR}. In this work, we present a novel approach utilizing spatial conditioning techniques within a foundation model to transform satellite SAR imagery into airborne SAR representations. Additionally, we demonstrate that our pipeline is effective for bridging the realism of simulated images generated by ONERA's physics-based simulator EMPRISE \cite{empriseem_ai_images}. Our method explores a key application of AI in advancing SAR imaging technology. To the best of our knowledge, we are the first to introduce this approach in the literature. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03844 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Spaceborne to Airborne: SAR Image Synthesis Using Foundation Models for Multi-Scale Adaptation Debuysere, Solene Trouve, Nicolas Letheule, Nathan Leveque, Olivier Colin, Elise Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition The availability of Synthetic Aperture Radar (SAR) satellite imagery has increased considerably in recent years, with datasets commercially available. However, the acquisition of high-resolution SAR images in airborne configurations, remains costly and limited. Thus, the lack of open source, well-labeled, or easily exploitable SAR text-image datasets is a barrier to the use of existing foundation models in remote sensing applications. In this context, synthetic image generation is a promising solution to augment this scarce data, enabling a broader range of applications. Leveraging over 15 years of ONERA's extensive archival airborn data from acquisition campaigns, we created a comprehensive training dataset of 110 thousands SAR images to exploit a 3.5 billion parameters pre-trained latent diffusion model \cite{Baqu2019SethiR}. In this work, we present a novel approach utilizing spatial conditioning techniques within a foundation model to transform satellite SAR imagery into airborne SAR representations. Additionally, we demonstrate that our pipeline is effective for bridging the realism of simulated images generated by ONERA's physics-based simulator EMPRISE \cite{empriseem_ai_images}. Our method explores a key application of AI in advancing SAR imaging technology. To the best of our knowledge, we are the first to introduce this approach in the literature. |
| title | From Spaceborne to Airborne: SAR Image Synthesis Using Foundation Models for Multi-Scale Adaptation |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.03844 |