A unified model of noise estimation, band rejection, and de-noising for hyperspectral images

As hyperspectral images (HSIs) often suffer from various kinds of degradation, HSI de-noising becomes a challenging task, which can improve not only the visual appearance but also the performance of subsequent applications. Since the noise level in each band is commonly not uniform, many methods of de-noising all bands equally may fail in some cases. Therefore, this study proposes a bilayer model for HSI noise estimation, band rejection, and de-noising, which is in a unified framework of low-rank representation (LRR). Based on channel-dependent noise estimation, the first layer is used to make the noise level in each band more uniform and perform an efficient band rejection. Then in the second layer, a further de-noising that can deal with the mixed noise in HSIs is performed. Both simulated and real data sets are used for experiments, which demonstrate that the proposed model can achieve better results than several other state-of-the-art methods in HSI de-noising.