The patch extraction layer is used to extract dense patches from the input, and to represent them using convolutional filters. SRCNN is a simple CNN architecture consisting of three layers: one for patch extraction, non-linear mapping, and reconstruction. The most popular method, SRCNN, was also the first to use deep learning, and has achieved impressive results.
The methods under this bracket use traditional techniques–like bicubic interpolation and deep learning–to refine an upsampled image.
We'll look at several example algorithms for each.
There are many methods used to solve this task. The task of the neural network is to find the inverse function of degradation using just the HR and LR image data. The degradation parameters D and $\sigma$ are unknown only the high resolution image and the corresponding low resolution image are provided. Low resolution images can be modeled from high resolution images using the below formula, where D is the degradation function, I y is the high resolution image, I x is the low resolution image, and $\sigma$ is the noise.
You can also run the code for one of the models we'll cover, ESPCN, for free on the ML Showcase. In this article we will discuss the theory involved, various techniques used, loss functions, metrics, and relevant datasets.