PromptHSI: Universal Hyperspectral Image Restoration With Vision–Language Modulated Frequency Adaptation
Journal
IEEE Transactions on Geoscience and Remote Sensing
Journal Volume
64
Start Page
1
End Page
16
ISSN
0196-2892
1558-0644
Date Issued
2026-02-03
Author(s)
Cheng, Ching-Heng
Lee, Chia-Ming
Liao, Wo-Ting
Lin, Yu-Fan
Cheng, Yi-Ching
Yang, Fu-En
Hsu, Chih-Chung
Abstract
Recent advances in all-in-one (AiO) RGB image restoration have demonstrated the effectiveness of prompt learning in handling multiple degradations within a single model. However, adapting these approaches to hyperspectral image (HSI) restoration poses significant challenges due to the domain gap between RGB and HSI features, information loss in visual prompts under severe composite degradations, and difficulties in capturing HSI-specific degradation patterns via text prompts. To address these limitations, we introduce PromptHSI, the first universal AiO HSI restoration framework that is both prompt-guided and frequency-aware. By incorporating frequency-aware feature modulation, which uses frequency analysis to decouple complex composite degradations, and by employing vision-language model (VLM)-guided prompt learning, our approach decomposes text prompts into intensity and bias controllers that effectively guide the restoration process while mitigating domain discrepancies. Extensive experiments demonstrate that our unified architecture excels at both fine-grained detail recovery and global information restoration across diverse degradation scenarios, highlighting its significant potential for practical remote sensing applications.
Subjects
All-in-one (AiO) image restoration
frequency modulation
hyperspectral image (HSI) restoration
vision-language model
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Type
journal article