光谱超分辨率：使用空间-光谱残差算子网络
Spectral Super-Resolution using Spatial-Spectral Residual Operator Networks
浏览论文内容
中文总结 AI 辅助
本研究提出SSRON深度算子网络，将光谱超分辨率视为算子学习问题，实现从降采样光谱到连续光谱的映射，在Sentinel-2A到EMIT任务上超越基线，并具备零样本预测和更细波长估计能力。
中文摘要 AI 辅助
多光谱卫星图像的光谱超分辨率能够以适中的成本实现高时间分辨率和空间分辨率的高光谱卫星图像，显著提高高光谱遥感的应用性。该任务本质上是不适定的，因此非常适合基于深度学习的方法。在本研究中，光谱超分辨率任务被构建为一个算子学习问题，并提出了SSRON作为一种深度算子网络，能够有效地学习从降采样光谱到连续光谱的函数到函数映射。该模型被训练用于将类似Sentinel-2A的多光谱图像超分辨率重建为EMIT图像。与基线模型相比，SSRON在所有指标上均取得了优越的性能。该模型还展示了零样本光谱超分辨率能力，能够预测训练中未见过的波段。此外，其连续输出的公式表明其具有在比原生传感器更细的波长间隔上估计光谱的潜力。这些结果显示了SSRON的潜力，并将算子学习确立为光谱超分辨率的一个有前景的方向。
英文摘要
Spectral super-resolution of multispectral satellite images can enable high temporal- and spatial-resolution hyperspectral satellite imagery at a modest cost, significantly increasing the applicability of hyperspectral remote sensing. This task is inherently ill-posed, making it well-suited for deep learning-based methods. In this study, the spectral super-resolution task is framed as an operator learning problem, and SSRON is proposed as a Deep Operator Network that effectively learns function-to-function mappings from downsampled spectra to continuous spectra. The model is trained to super-resolve Sentinel-2A-like multispectral imagery to EMIT images. Compared to baseline models, SSRON achieves superior performance across all metrics. The model also demonstrates zero-shot spectral super-resolution capability by predicting bands unseen during training. Furthermore, its continuous-output formulation suggests the potential to estimate spectra at finer wavelength intervals than the native sensor. These results suggest the potential of SSRON and establishes operator learning as a promising direction for spectral super-resolution.
发表机构
- California Institute of Technology（加州理工学院）
机构由 AI 辅助整理，请以论文原文为准。
