Unified Blind Method for Multi-Image Super-Resolution and Single/Multi-Image Blur Deconvolution

Abstract

This paper presents, for the first time, a unified blind method for multi-image super-resolution (MISR or SR), single-image blur deconvolution (SIBD), and multi-image blur deconvolution (MIBD) of low-resolution (LR) images degraded by linear space-invariant (LSI) blur, aliasing, and additive white Gaussian noise (AWGN). The proposed approach is based on alternating minimization (AM) of a new cost function with respect to the unknown high-resolution (HR) image and blurs. The regularization term for the HR image is based upon the Huber-Markov random field (HMRF) model, which is a type of variational integral that exploits the piecewise smooth nature of the HR image. The blur estimation process is supported by an edge-emphasizing smoothing operation, which improves the quality of blur estimates by enhancing strong soft edges toward step edges, while filtering out weak structures. The parameters are updated gradually so that the number of salient edges used for blur estimation increases at each iteration. For better performance, the blur estimation is done in the filter domain rather than the pixel domain, i.e., using the gradients of the LR and HR images. The regularization term for the blur is Gaussian (L2 norm), which allows for fast noniterative optimization in the frequency domain. We accelerate the processing time of SR reconstruction by separating the upsampling and registration processes from the optimization procedure. Simulation results on both synthetic and real-life images (from a novel computational imager) confirm the robustness and effectiveness of the proposed method.

Super-resolution by polar Newton–Thiele׳s rational kernel in centralized sparsity paradigm

“…We refer to [2,3,[10][11][12][13][14][15][16]18,19,[23][24][25][27][28][29][30][32][33][34][35] for other SR methods. In the SR reconstruction algorithm, Sun et al [11] used the gradient profile prior which was learned from plenty of natural images.…”

Image Resolution Enhancement Using Blind Techniques -a Survey

“…In [3], interpolation based blind super resolution method applied; here the processing time is 40 seconds.…”

“…In [3],adaptive BSR algorithm used in which the cost function is based on Alternating Minimization approach, the regularization for image and blur are Huber Markov Random field Model and Gaussian. The estimated PSNR value is 29 dB.…”

Blind Restoration of Remote Sensing Images by a Combination of Automatic Knife-Edge Detection and Alternating Minimization

“…According to the blur identification stages, the blind restoration methods can be classified into two categories: (1) methods that estimate the PSF before the image is identified, as separate procedures [5,[16][17][18]; and (2) methods that estimate the PSF and the image simultaneously in a joint procedure [19][20][21][22][23][24][25][26][27][28][29][30][31][32][33]. In our work, we mainly focus on the second type of method.…”

“…Similar models have since been developed by the use of a total variation (TV) prior [23][24][25]31], a Huber-Markov random field (HMRF) prior [28], or a sparse prior [30,32]. The optimization methods have also developed from the steepest descent method, conjugate gradient (CG) [22,24,28,29], and Bregman iteration [25] to split Bregman [31] or augmented Lagrangian methods [32]. The straightforward AM framework has been proven to be competitive when compared to much more complicated methods [32,34], and is a good strategy to remove the blurring effect in images.…”