用可解释的度量提示，让高光谱图像修复模型自适应未知退化。
Degradation-Aware Metric Prompting for Hyperspectral Image Restoration
- 通过空间-光谱度量生成退化提示，引导模型动态选择专家
- 在多个数据集上达到顶尖性能，零样本迁移能力突出
- 适合需要泛化到未知退化场景的研究者和工程师
统一的高光谱图像（HSI）修复旨在恢复多种退化。然而，现有方法常依赖不切实际的显式先验或黑箱表示，易过拟合训练分布，限制了对未见场景的泛化能力。为此，我们提出退化感知度量提示（DAMP）框架，通过可解释的空间-光谱度量刻画多维退化特征，生成退化提示（DP），使模型能捕捉任务间共性并适应未知噪声。核心是退化自适应专家混合（DAMoE），其中空间-光谱自适应模块（SSAMs）作为专家，通过可学习融合系数针对不同退化程度进行专业化处理；以DP为门控路由，动态激活匹配特定退化特征的专家。在自然与遥感HSI数据集上的大量实验表明，DAMP达到当前最优性能，并在未见修复任务中展现卓越零样本泛化能力。代码已公开于https://github.com/MiliLab/DAMP。
原文摘要 · Abstract (English)
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. Code is publicly available at \href{DAMP}{https://github.com/MiliLab/DAMP}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。