Unsupervised Alternating Optimization for Blind Hyperspectral Imagery Super-resolution
This work tackles the problem of poor generalization of HSI SR methods to real-world data for researchers and practitioners working with hyperspectral imaging, offering an incremental improvement by better handling degeneration models.
This paper addresses the poor performance of existing Hyperspectral Imagery (HSI) super-resolution (SR) methods on real data due to discrepancies in predefined degeneration models. The authors propose an unsupervised blind HSI SR method that uses an alternating optimization-based deep framework to estimate degeneration models and reconstruct the latent image, achieving superior performance on three benchmark datasets.
Despite the great success of deep model on Hyperspectral imagery (HSI) super-resolution(SR) for simulated data, most of them function unsatisfactory when applied to the real data, especially for unsupervised HSI SR methods. One of the main reason comes from the fact that the predefined degeneration models (e.g. blur in spatial domain) utilized by most HSI SR methods often exist great discrepancy with the real one, which results in these deep models overfit and ultimately degrade their performance on real data. To well mitigate such a problem, we explore the unsupervised blind HSI SR method. Specifically, we investigate how to effectively obtain the degeneration models in spatial and spectral domain, respectively, and makes them can well compatible with the fusion based SR reconstruction model. To this end, we first propose an alternating optimization based deep framework to estimate the degeneration models and reconstruct the latent image, with which the degeneration models estimation and HSI reconstruction can mutually promotes each other. Then, a meta-learning based mechanism is further proposed to pre-train the network, which can effectively improve the speed and generalization ability adapting to different complex degeneration. Experiments on three benchmark HSI SR datasets report an excellent superiority of the proposed method on handling blind HSI fusion problem over other competing methods.