A Proximal Approach to Denoising Hyperspectral Images under Mixed-Noise Model

Abstract: In this paper, we present a proximal approach to hyperspectral image denoising adapted to the mixed noise behaviour of hyperspectral data; named Hyperspectral Image Proximal Denoiser (HSIProxDenoiser). Combination of Gaussian-impulse noise has been handled under Maximum a posteriori framework using two data fidelity terms. We have incorporated prior information about the data in the form of two regularization terms; namely Tikhonov-Miller (TM) and Total Variation (TV). Since TV possesses feature selection capability by setting some of the co-efficients to zero, it works well when there are small number of significant features. On the other hand, TM works well if there are large number of similar features. Hence, including both regularization terms can help achieve desired denoising performance. The resultant optimization problem is solved using a variant of Primal-Dual Hybrid Gradient (PDHG) by splitting the former into different functions and calculating their proximal operators individually. Experimental results over both synthetic as well as real HSI data validate the potential of the proposed technique both visually and in terms of the quantitative metrics. (Paper) (Supplementary text 1) (Supplementary Text 2)