Abstract
Existing hyperspectral image (HSI) super-resolution methods fusing a high-resolution RGB image (HR-RGB) and a low-resolution HSI (LR-HSI) always rely on spatial degradation and handcrafted priors, which hinders their practicality. To address these problems, we propose a novel, to the best of our knowledge, method with two transfer models: a window-based linear mixing (W-LM) model and a feature transfer model. Specifically, W-LM initializes a high-resolution HSI (HR-HSI) by transferring the spectra from the LR-HSI to the HR-RGB. By using the proposed feature transfer model, the HR-RGB multi-level features extracted by a pre-trained convolutional neural network (CNN) are then transferred to the initialized HR-HSI. The proposed method fully exploits spectra of LR-HSI and multi-level features of HR-RGB and achieves super-resolution without requiring the spatial degradation model and any handcrafted priors. The experimental results for 32 × super-resolution on two public datasets and our real image set demonstrate the proposed method outperforms eight state-of-the-art existing methods.
© 2022 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Xuheng Cao, Yusheng Lian, Zilong Liu, Han Zhou, Bin Wang, Wan Zhang, and Beiqing Huang
Opt. Lett. 47(19) 5184-5187 (2022)
Yufei Yang, Wenqian Dong, Song Xiao, Tongzhen Zhang, and Jiahui Qu
Opt. Lett. 47(6) 1371-1374 (2022)
Xin Tian, Ying Xiao, Rui Liu, Fang He, and Jiayi Ma
Opt. Lett. 47(9) 2230-2233 (2022)