Video Super Resolution by Neural Network: A Theoretical Aspect

Abstract

The paper explores literature on the video super resolution by neural network, with all essential basics related to it. The extensive applicability and need of enhanced resolution becomes attraction for researchers. The limitations of traditional methods gives rise to the new generation of neural network based super resolution. The neural networks are well known for parallel and fast computation of data. But embedding a neural network with challenging super resolution era has come up with benefits as well as drawbacks. Still the researchers are working on the challenges like, limited practical feasibility and utility, accuracy at the time cost, complexity, etc. This paper is useful for new researchers to get information about the basics of super resolution and neural network, relative study of learning processes, comparative summarization of neural network architecture used for resolution improvement.