Is it difficult to run srgan super resolution?

Disaster.

The concept of super-resolution was first used in the 1960s. It refers to the technology of generating high-resolution images from low-resolution images through a certain algorithm or model, and recovering as much detailed information as possible, also known as extra-spectral information.

push method.

However, in the early stages of research, the spectrum extrapolation method was only used for simulations under some assumed conditions and was not widely recognized.

It was not until the single-image super-resolution method was proposed that super-resolution technology began to be widely researched and applied.

At present, it has become an important research direction in the field of image enhancement and even computer vision.

Generally speaking, the algorithm model of traditional learning methods is relatively simple and the training set is relatively small.

Deep learning methods generally refer to convolutional neural network methods that use large amounts of data to train, and are also currently a hot topic in academic research.

Therefore, next I will focus on the development process of super-resolution methods based on deep learning.