Video super resolution based on non-local regularization and reliable motion estimation

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.…”

“…Tai et al [14] combined edge-directed SR with learningbased SR to obtain good results and extended edgedirected SR to get detail from a single exemplar image. After analyzing the reasons for the inaccuracy of motion estimation, Lu et al [25] proposed a multi-lateral filter to regularize the process of motion estimation, and then introduced a non-local prior to regularize the HR image reconstruction, and finally the two regularizations were incorporated into one maximum a posteriori estimation model. In contrast to the traditional exemplar-based hallucination methods, Yue et al [12] proposed a novel SR scheme for landmark images by retrieving correlated images from the Internet.…”

Video super-resolution using an adaptive superpixel-guided auto-regressive model

“…Liu et al [26] propose a Bayesian approach for adaptive video super-resolution by simultaneously estimating underlying motion, blur kernel and noise level. Lu et al [27] design a Maximum a Posteriori (MAP) estimation model by considering two regularizations: motion estimation based on a multi-lateral filter and high-resolution image reconstruction based on a non-local prior. Liao et al [28] propose a data fusion algorithm based on non-local normalized convolution to achieve robust super-resolution.…”

Single-image super-resolution using iterative Wiener filter based on nonlocal means

“…There are two major categories of these algorithms; they are reconstruction-based and learning-based. Reconstructionbased algorithms [7][8][9][10][11][21][22][23] apply the prior knowledge to regularize the solution. Edges or gradients [9][10][11] are the main features used as the prior knowledge.…”