Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolution
This work provides an incremental improvement for researchers and applications requiring high-resolution hyperspectral images, particularly in remote sensing, by enhancing spectral reconstruction and classification accuracy.
This paper addresses the problem of obtaining high spatial resolution hyperspectral images from high-resolution multispectral images. The proposed method, an optimization-driven convolutional neural network guided by spectral response functions, demonstrates spectral enhancement effects on natural and remote sensing datasets, and improves classification results on remote sensing data.
Hyperspectral images are crucial for many research works. Spectral super-resolution (SSR) is a method used to obtain high spatial resolution (HR) hyperspectral images from HR multispectral images. Traditional SSR methods include model-driven algorithms and deep learning. By unfolding a variational method, this paper proposes an optimization-driven convolutional neural network (CNN) with a deep spatial-spectral prior, resulting in physically interpretable networks. Unlike the fully data-driven CNN, auxiliary spectral response function (SRF) is utilized to guide CNNs to group the bands with spectral relevance. In addition, the channel attention module (CAM) and reformulated spectral angle mapper loss function are applied to achieve an effective reconstruction model. Finally, experiments on two types of datasets, including natural and remote sensing images, demonstrate the spectral enhancement effect of the proposed method. And the classification results on the remote sensing dataset also verified the validity of the information enhanced by the proposed method.