Edge-preserving image super-resolution via low rank and total variation model

摘要

#$%^&*AU2020100462A420200430.pdf#####ABSTRACT The purpose of image super-resolution is to recover the corresponding high-resolution which can meet the corresponding needs from the low-resolution image. Because the low resolution image is blurred and noisy, some traditional methods in the past can not get good reconstruction results. In this patent, a method of low rank, total variation regularization and gradient regularization based on nearest neighbor regression are used to recover high-quality images. Block-Matching 3D filtering (BM3D) is used to make our method more robust to noise. The neighborhood regression method is used to reconstruct the low-resolution image to get more details. Low rank prior can be used to complete a matrix which principle is some rows and columns in the matrix can be linearly represented by other rows and columns. Total variation prior can effectively remove noise and process image edge information reasonably. Alternating direction method of multipliers (ADMM) method is used to optimize the algorithm and get better image super-resolution results.1/1 DRAWINGS (a)BICUBIC (b)LRTV (c)SCSR (e)NCSR (f)OURS (h)ORIGINAL Figure 1