SRCNN-白红宇

SRCNN

阅读量：6041 次

发布时间：2019-06-20

本文共 2100 字，大约阅读时间需要 7 分钟。

超分的开篇之作，2014 ECCV 港中文 Chao Dong

三层网络，文中还对各层网络的意义做出了解释

使用caffe训练模型，matlab做inference，代码见 http://mmlab.ie.cuhk.edu.hk/projects/SRCNN.html

700*700像素的图重建出来需要30s+，效果还是比较朦胧

可以用自己的图片做一下直观了解

path = 'E:\Download\超分辨率\test\test';list = dir(path);for i1 = 1: size(list,1)    name = list(i1).name;    if name == '.'        continue;    end    fullName = fullfile(path, name);    demo_SR(fullName);   % 需要把作者的demo源文件改为functionend

评估方法

计算PSNR、SSIM，计算的方式可以参见VDSR的matlab代码

常用评估数据集 set5，set14，B100，urban100，之后的新paper，还用了manga109、部分DIV2K等

用二维坐标表示性能也相当直观

缺点：

1、Works for only a single scale

2、卷积感受野太小

3、学习速率 1e-5 太慢，需要加快训练速度。而且inference的速度也比较慢

如何训练model

关于训练数据的说明：

For a fair comparison with traditional example-based methods, we use the same training set, test sets, and protocols as in [20]. Specically, the training set consists of 91 images. The Set5 [2] (5 images) is used to evaluate the performance of upscaling factors 2, 3, and 4, and Set14 [28] (14 images) is used to evaluate the upscaling factor 3. In addition to the 91-image training set, we also investigate a larger training set in Section 5.2.

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

http://www.vision.ee.ethz.ch/~timofter/ICCV2013_ID1774_SUPPLEMENTARY/index.html

而cvpr2018的SR文章使用的训练集，基本就是比较大的数据集了，其实选什么都可以的，只要不包含test data即可。

DIV2K consists of 800 training images, 100 validation images, and 100 test images. We train all of our models with 800 training images and use 5 validation images in the training process. For testing, we use five standard benchmark datasets: Set5 [1], Set14 [33], B100 [18], Urban100 [8], and Manga109 [19]. The SR results are evaluated with PSNR and SSIM [32] on Y channel (i.e., luminance) of transformed YCbCr space.