Image restoration is the operation of taking a corrupt/noisy image and estimating the clean, original image.
Deep learning is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. Learning can be supervised, semi-supervised or unsupervised.
.Image restoration using deep learning
Recently, image restoration method using deep learning is widely used due to development of computing technology and development of big data.
CNN (Convolutional Neural Networks)
Becoming easy to get more data and improved computing power, CNN started to be used in various area. For example, Super-Resolution and removing compression artifacts. So we are planning to enhance quality of video compression by using CNN.