Hyperspectral image super-resolution reconstruction based on image partition and detail enhancement

Abstract The hyperspectral image (HSI) super-resolution (SR) reconstruction has attracted much attention and been used widely in various study fields due to its low requirements on hardware in practice. However, the distribution of image information is uneven. And HSI is treated equally during the process of super-resolution reconstruction. It is time consuming and many details cannot be extracted specifically. In this paper, a new method named MSDESR (multilevel streams and detail enhancement) is proposed to reconstruct HSI according to its uneven distribution of spatial information. The MSDESR consists of a submap shunt block, a high-low frequency information extraction with detail enhancement block, and a partition image reconstruction block. Firstly, the submap shunk block is designed to pre-classify hyperspectral images. The images are divided into complex and simple parts according to the spatial information distribution of the reconstructed submap. Secondly, the multiscale Retinex with detail enhancement algorithm is constructed to purify high-frequency noise-contaminated and enhance the image details by separating the samples into high and low frequency information. Finally, branching networks of different complexities are designed to reconstruct the images with high credibility and clear content. In this paper, datasets of QUST-1, Pavia University and Chikusei are applied in the experiments. The results show that, the MSDER outperforms state-of-the-art CNN-based methods in terms of quantitative metrics and visual quality, with quantities of 4.18% and 9.35% in the SRE and MPSNR metrics, respectively. Overall, the MSDER performs well in hyperspectral image super-resolution reconstruction, which is time saving and preserves the details of spatial information.