EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel VLM-Guided Diffusion Model for Remote Sensing Image Super-Resolution

Mingyu Sung, Mu-Gyeong Gong, Seung-Jae Ham, Il-Min Kim, Sangseok Yun, Jae-Mo Kang

IEEE Geoscience and Remote Sensing Letters · 2025 · 22 · 1-5

DOI: 10.1109/lgrs.2025.3608178 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Geoscience and Remote Sensing Letters, 2025. Verfasst von Mingyu Sung und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea (NRF) grant funded by the Korea Government, Institute of Information and Communications Technology Planning and Evaluation (IITP)-Innovative Human Resource Development for Local Intellectualization Progr….

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Super-resolution (SR) of remote sensing imagery based on generative AI models is vital for practical applications such as urban planning and disaster assessment. However, current approaches suffer from poor performance tradeoffs among the pivotal, yet competing, objectives: perceptual quality, factual accuracy, and inference speed. To break through this limitation, we propose a novel and high-performing two-stage SR framework for remote sensing imagery based on a generative diffusion model. First, in Stage 1, factually grounded base images are generated by employing a guidance-free diffusion process relying solely on the original low-resolution (LR) images, such that the risk of semantic hallucination can be effectively mitigated. The generated images are refined subsequently in Stage 2 such that high-frequency details for SR quality can be restored via our customized and innovative guidance mechanism with a vision–language model (VLM) and a ControlNet, and a dynamic inference acceleration technique is applied to ensure efficiency. Extensive experimental results confirm that our proposed framework excels in perceptual quality—achieving top contrastive language—image pretraining-based image quality assessment (CLIP-IQA) scores—and in structural integrity while achieving robust performance. In particular, it enables reliable, high-fidelity SR for large-scale, real-world remote sensing pipelines by surpassing the conventional fidelity–hallucination tradeoff at practical inference speed. The source code is available at https://github.com/Bluear7878/Remote-Sensing-Vision-Language-Diffusion-Model

Förderung

  • National Research Foundation of Korea (NRF) grant funded by the Korea Government
  • Institute of Information and Communications Technology Planning and Evaluation (IITP)-Innovative Human Resource Development for Local Intellectualization Progr…

Zitieren

APA

Sung, M., Gong, M., Ham, S., Kim, I., Yun, S., & Kang, J. (2025). A Novel VLM-Guided Diffusion Model for Remote Sensing Image Super-Resolution. IEEE Geoscience and Remote Sensing Letters, 22, 1-5. https://doi.org/10.1109/lgrs.2025.3608178

Vancouver

Sung M, Gong M, Ham S, Kim I, Yun S, Kang J. A Novel VLM-Guided Diffusion Model for Remote Sensing Image Super-Resolution. IEEE Geoscience and Remote Sensing Letters. 2025;22:1-5. doi:10.1109/lgrs.2025.3608178

BibTeX
@article{Sung2025,
  author = {Sung, Mingyu and Gong, Mu-Gyeong and Ham, Seung-Jae and Kim, Il-Min and Yun, Sangseok and Kang, Jae-Mo},
  title = {A Novel VLM-Guided Diffusion Model for Remote Sensing Image Super-Resolution},
  journal = {IEEE Geoscience and Remote Sensing Letters},
  year = {2025},
  volume = {22},
  pages = {1--5},
  doi = {10.1109/lgrs.2025.3608178}
}
Kostenlos starten →