Learning Deep Resonant Prior for Hyperspectral Image Super-Resolution

The hyperspectral image super-resolution (HSISR) task has been widely studied, and significant progress has been made by leveraging the deep convolution neural network (CNN) techniques. Nevertheless, the scarcity of training images hinders the research progress of the HSISR task. Moreover, the differences in imaging conditions and the number of spectral bands among different datasets make it very difficult to construct a unified deep neural network. In this article, we first present a nontraining-based HSISR method based on deep prior knowledge, which captures the image before restoring the high-resolution image by using the intrinsic characteristics of CNN. Then, we append a special network input processing module (IPM) onto the HSISR network to automatically adjust the structure of the input so that the choice of network structure is no longer limited, while the network design focuses on exploiting the spatial information of hyperspectral images (HSIs) and the correlation between spectral bands, making the method more suitable for HSISR tasks and greatly extending its applications. Extensive experimental results on the HSI datasets illustrate the effectiveness of the proposed method, and we have got comparable results with the state-of-the-art methods while requiring no training samples.