Extending Semantic Interpretation and Visual Understanding of SAR Data via Generative Translation Models
GEO DATA · 31.03.2026 · 8 (1) · 44-54
DOI: 10.22761/gd.2026.0004 ↗Kurz gefasst
Fachartikel in der Zeitschrift GEO DATA, erschienen am 31.03.2026. Verfasst von Min Kim und 2 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Research Foundation of Korea, Ministry of Science and ICT.
Abstract (Originalsprache)
Synthetic aperture radar (SAR) offers critical all-weather observation capabilities, yet its interpretation remains challenging due to inherent speckle noise and non-intuitive scattering characteristics. Consequently, directly applying vision-language models (VLMs) trained on natural images to the SAR domain is limited by significant modality gaps and the scarcity of high-quality SAR-text datasets. To overcome these challenges, this study proposes a two-stage framework that leverages SAR-to-optical translation to bridge the domain gap. First, we introduce a conditional Brownian Bridge Diffusion Model integrated with a SAR feature guidance module. This approach transforms SAR images into optical-like representations while preserving structural fidelity, thereby addressing the geometric distortions and hallucinations common in generative adversarial network (GAN)-based methods. Second, the translated images are analyzed by a domain-adapted VLM, utilizing the GeoRSCLIP visual encoder and a LoRA-tuned LLaVA model to generate precise semantic captions. Experimental results using Sentinel-1 and Sentinel-2 datasets demonstrate that the proposed translation model outperforms existing GAN models in terms of PSNR and SSIM. Furthermore, the framework achieves significant improvements in captioning metrics, including BLEU, ROUGE-L, and BERT-Score, compared to direct SAR interpretation. This study validates that high-fidelity modality translation can effectively extend the reasoning capabilities of pre-trained VLMs to the SAR domain without requiring extensive SAR-specific annotations.
Förderung
- National Research Foundation of Korea
- Ministry of Science and ICT
Zitieren
APA
Kim, M., Lee, K., & Park, S. (2026). Extending Semantic Interpretation and Visual Understanding of SAR Data via Generative Translation Models. GEO DATA, 8(1), 44-54. https://doi.org/10.22761/gd.2026.0004
Vancouver
Kim M, Lee K, Park S. Extending Semantic Interpretation and Visual Understanding of SAR Data via Generative Translation Models. GEO DATA. 2026;8(1):44-54. doi:10.22761/gd.2026.0004
BibTeX
@article{Kim2026,
author = {Kim, Min and Lee, Kyungil and Park, Seonyoung},
title = {Extending Semantic Interpretation and Visual Understanding of SAR Data via Generative Translation Models},
journal = {GEO DATA},
year = {2026},
volume = {8},
number = {1},
pages = {44--54},
doi = {10.22761/gd.2026.0004}
}
EUVIMED