image super -resolution as sparse representation of raw image patches代码解读之超分辨率重建

最新推荐文章于 2022-11-08 20:24:06 发布

化生。

最新推荐文章于 2022-11-08 20:24:06 发布

阅读量3.6k

点赞数 4

分类专栏：超分辨率重建稀疏表示

本文链接：https://blog.youkuaiyun.com/w1378236582/article/details/80527249

版权

本文解读杨建超教授公开的超分辨率重建代码，重点介绍无需重新训练字典，直接运行实现图像超分辨率的过程，包括关键步骤如特征提取，并计算信噪比。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

杨建超教授公布的代码，字典已经训练好，不需要重新训练。可以直接运行进行超分辨率的重建。

1、

% =========================================================================
% Simple demo codes for image super-resolution via sparse representation
%
% Reference
%   J. Yang et al. Image super-resolution as sparse representation of raw
%   image patches. CVPR 2008.
%   J. Yang et al. Image super-resolution via sparse representation. IEEE 
%   Transactions on Image Processing, Vol 19, Issue 11, pp2861-2873, 2010
%
% Jianchao Yang
% ECE Department, University of Illinois at Urbana-Champaign
% For any questions, send email to jyang29@uiuc.edu
% =========================================================================

clear all; clc;

% read test image
im_l = imread('Data/Testing/input.bmp');

% set parameters
lambda = 0.2;                   % sparsity regularization,lambda是个常量正系数，平衡下稀疏系数alpha的重要性
overlap = 4;                    % the more overlap the better (patch size 5x5)重叠
up_scale = 2;                   % scaling factor, depending on the trained dictionary
maxIter = 20;                   % if 0, do not use backprojection 反投影

% load dictionary加载之前训练好的字典
load('Dictionary/D_1024_0.15_5.mat');

最低0.47元/天解锁文章