Improved Super-Resolution Convolution Neural Network for Large Images

TL;DR

This paper introduces a refined SRCNN architecture with symmetric padding, random learning, and residual learning to improve super-resolution quality for large images, reducing artifacts and enhancing performance.

Contribution

The paper presents a novel SRCNN-based model with specific architectural improvements tailored for large image super-resolution tasks.

Findings

The proposed model outperforms existing state-of-the-art methods in super-resolution accuracy.

The refined architecture reduces boundary artifacts in large image super-resolution.

Experimental results demonstrate significant performance improvements over previous approaches.

Abstract

Single image super-resolution (SISR) is a very popular topic nowadays, which has both research value and practical value. In daily life, we crop a large image into sub-images to do super-resolution and then merge them together. Although convolution neural network performs very well in the research field, if we use it to do super-resolution, we can easily observe cutting lines from merged pictures. To address these problems, in this paper, we propose a refined architecture of SRCNN with 'Symmetric padding', 'Random learning' and 'Residual learning'. Moreover, we have done a lot of experiments to prove our model performs best among a lot of the state-of-art methods.