Hyperspectral Image Restoration Via Total Variation Regularized Low-Rank Tensor Decomposition

Abstract

Hyperspectral images (HSIs) are often corrupted by a mixture of several types of noise during the acquisition process, e.g., Gaussian noise, impulse noise, dead lines, stripes, and many others. Such complex noise could degrade the quality of the acquired HSIs, limiting the precision of the subsequent processing. In this paper, we present a novel tensor-based HSI restoration approach by fully identifying the intrinsic structures of the clean HSI part and the mixed noise part respectively. Specifically, for the clean HSI part, we use tensor Tucker decomposition to describe the global correlation among all bands, and an anisotropic spatial-spectral total variation (SSTV) regularization to characterize the piecewise smooth structure in both spatial and spectral domains. For the mixed noise part, we adopt the 1 norm regularization to detect the sparse noise, including stripes, impulse noise, and dead pixels. Despite that TV regulariztion has the ability of removing Gaussian noise, the Frobenius norm term is further used to model heavy Gaussian noise for some real-world scenarios. Then, we develop an efficient algorithm for solving the resulting optimization problem by using the augmented Lagrange multiplier (ALM) method. Finally, extensive experiments on simulated and real-world noise HSIs are carried out to demonstrate the superiority of the proposed method over the existing state-of-the-art ones.Index Terms-Hyperspectral image (HSI), mixed noise, low rank tensor decomposition, total variation (TV).

Multipass SAR Interferometry Based on Total Variation Regularized Robust Low Rank Tensor Decomposition

“…µ can be initially set as 10 −2 and updated in each iteration by µ := min(ηµ, µ max ), where η = 1.1. As introduced in [45], [47], [48], γ can be set as 100/ √ I 1 I 2 . In our experiences, α is selected in a range from 0 to 0.2 and β can be chosen between 0 to 10.…”

Unified Low-Rank Matrix Estimate via Penalized Matrix Least Squares Approximation

“…Before introducing PMLSA, we consider how to obtain −1 j in (5). For the univariate model Y j = XB j +E j , Koenker [23] indicated that the asymptotic covariance of the estimationB j has the common property…”

Tensor p-shrinkage nuclear norm for low-rank tensor completion

“…In particular, multi-dimensional arrays (i.e., tensors) provide a natural representation form for these data. Tensor, which is regarded as a multi-linear generalization of matrix/vector, can mathematically model the multi-dimensional data structures, making tensor learning so attractive that there are increasing applications in computer vision [1][2][3][4], machine learning [5,6], signal processing [7,8], and pattern recognition [9] in recent years. Unfortunately, the challenge of missing elements in the actually observed tensors limits its applications.…”

“…Obviously, the difference among the existing LRTC models mainly lies in the choice of f . Although various tensor rank surrogates [3,6,18] are proposed to approximate the tensor rank, they all face some challenges in practical applications. According to the CP decomposition [15], Friedland et al [18] claimed that the CP-rank could be relaxed it with CP tensor nuclear norm (CNN), which is a convex surrogate that can be defined as:…”