无需预训练，单张图像即可修复高光谱图像缺失区域。
Hyperspectral Diffusion Equivariant Imaging (HyDiff-EI): A Self-supervised Framework for Hyperspectral Image Inpainting
- 基于扩散模型与对称性约束，直接从单张受损图像学习修复。
- 在无噪声和含噪场景下均显著优于现有自监督方法。
- 适合传感器配置多变、标注数据稀缺的遥感实际应用。
本文提出一种新型高光谱图像修复框架HyDiff-EI，解决高光谱图像（HSI）缺失问题。不同于依赖大规模预训练的传统扩散方法，HyDiff-EI采用测试时优化机制，仅需单张受损的高光谱图像即可直接学习修复。针对无监督修复的病态性，该框架在扩散过程中嵌入等变一致性约束，利用高光谱图像的几何对称性与内在特性，将生成式建模与自洽物理先验相融合。实验表明，结合扩散模型与等变先验能显著提升抗噪能力与泛化性能。在真实数据集Chikusei、Botswana和EMIT上的大量实验显示，无论在无噪声或含噪条件下，HyDiff-EI在修复质量上均优于现有自监督及扩散基算法。
原文摘要 · Abstract (English)
A novel Hyperspectral diffusion Equivariant Imaging (HyDiff-EI) framework for solving the hyperspectral image (HSI) inpainting problem has been presented here. Unlike conventional diffusion-based methods that rely on large-scale pretraining, HyDiff-EI is a test-time optimization framework that learns directly from a single corrupted HSI acquisition. This makes it flexible for different sensor configurations and particularly well-suited for practical remote sensing scenarios where large annotated hyperspectral datasets are limited. To address the ill-posed nature of unsupervised inpainting, we embed equivariant consistency constraints within the diffusion process. By leveraging the inherent geometric symmetries and intrinsic characteristics of HSIs, HyDiff-EI bridges the gap between generative diffusion modeling and self-consistent physical priors. We empirically show that coupling diffusion modeling with equivariant priors substantially enhances noise robustness and generalizability. Extensive experiments on real-world datasets including Chikusei, Botswana, and EMIT demonstrate that HyDiff-EI offers remarkable inpainting quality over existing self-supervised and diffusion-based algorithms in both noiseless and noisy cases.
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。