Image Super-Resolution Using TV Priori Guided Convolutional Network

TL;DR

This paper introduces a TV priori guided deep learning approach for single image super-resolution, combining TV prior information with neural networks to improve image up-sampling quality.

Contribution

It presents a novel TV priori guided CNN architecture that directly learns an end-to-end mapping for super-resolution, integrating TV prior into deep learning.

Findings

Enhanced super-resolution quality demonstrated

Effective integration of TV prior in CNN architecture

End-to-end learning approach for image up-sampling

Abstract

We proposed a TV priori information guided deep learning method for single image super-resolution(SR). The new alogorithm up-sample method based on TV priori, new learning method and neural networks architecture are embraced in our TV guided priori Convolutional Neural Network which diretcly learns an end to end mapping between the low level to high level images.