Update | Abstract | Models | Usage | Statement

2026.01.01

• The paper is post on arXiv! (arXiv)

• 2026.05.05

• The paper is accepted at ICML2026! (arXiv)

• 2026.06.15

• The source code released!

Unified hyperspectral image (HSI) restoration aims to recover diverse degradations within a single model. However, current methods often rely on impractical explicit priors or opaque black-box representations that overfit to training distributions, hampering generalization to unseen scenarios. To bridge this gap, we propose Degradation-Aware Metric Prompting (DAMP), a novel framework that characterizes multi-dimensional degradations through interpretable spatial-spectral metrics. These metrics serve as Degradation Prompts (DP), enabling the model to capture shared characteristics across tasks and adapt to unknown corruptions. Central to our framework is the Degradation-Adaptive Mixture-of-Experts (DAMoE), where Spatial-Spectral Adaptive Modules (SSAMs) serve as experts that utilize learnable fusion coefficients to specialize in distinct degradation degrees. By using DP as a gating router, DAMoE dynamically activates specialized experts tailored to the specific degradation profile. Extensive experiments on natural and remote sensing HSI datasets demonstrate that DAMP achieves state-of-the-art performance and exhibits exceptional zero-shot generalization on unseen restoration tasks.

Figure 1. (a) The architecture of the proposed DAMP framework. (b) The Degradation-Adaptive MoE.

Figure 2. (a) Comparison between explicit prompt-based methods and degradation-aware metric prompting approaches. (b) Confusion matrix for classifying five degradation types based on HFER, STU and SCM. (c) Distribution of different degradation types across the HFER, STU and SCM.

Figure 3. PSNR comparison with the state-of-the-art all-in-one methods: Inpainting, Super Resolution, Gaussian Deblurring, and Gaussian Denoising results are evaluated on the ARAD dataset after unified training, while Poisson Denoising and Motion Deblurring are reported as zero-shot results on the CAVE dataset. $[\cdot]$ denotes the range of PSNR values across different methods.

Coming Soon.

python main.py

@article{wang2025degradation,
  title={Degradation-Aware Metric Prompting for Hyperspectral Image Restoration},
  author={Wang, Binfeng and Wang, Di and Guo, Haonan and Fu, Ying and Zhang, Jing},
  journal={arXiv preprint arXiv:2512.20251},
  year={2025}
}

For any other questions please contact Bindeng Wabg at wbf_bit@163.com.