Research on Image Super-Resolution Reconstruction Mechanism based on Convolutional Neural Network

TL;DR

This paper proposes an enhanced deep convolutional neural network with residual learning and sub-pixel convolutional layers to improve image super-resolution, effectively capturing image features and preserving high-frequency details for better visual quality.

Contribution

The work introduces a novel CNN architecture with residual learning and sub-pixel layers specifically designed for super-resolution, outperforming traditional methods in detail preservation and image quality.

Findings

Superior performance on public datasets

Better edge and texture preservation

Outperforms bicubic and other learning-based methods

Abstract

Super-resolution reconstruction techniques entail the utilization of software algorithms to transform one or more sets of low-resolution images captured from the same scene into high-resolution images. In recent years, considerable advancement has been observed in the domain of single-image super-resolution algorithms, particularly those based on deep learning techniques. Nevertheless, the extraction of image features and nonlinear mapping methods in the reconstruction process remain challenging for existing algorithms. These issues result in the network architecture being unable to effectively utilize the diverse range of information at different levels. The loss of high-frequency details is significant, and the final reconstructed image features are overly smooth, with a lack of fine texture details. This negatively impacts the subjective visual quality of the image. The objective is to recover high-quality, high-resolution images from low-resolution images. In this work, an enhanced deep convolutional neural network model is employed, comprising multiple convolutional layers, each of which is configured with specific filters and activation functions to effectively capture the diverse features of the image. Furthermore, a residual learning strategy is employed to accelerate training and enhance the convergence of the network, while sub-pixel convolutional layers are utilized to refine the high-frequency details and textures of the image. The experimental analysis demonstrates the superior performance of the proposed model on multiple public datasets when compared with the traditional bicubic interpolation method and several other learning-based super-resolution methods. Furthermore, it proves the model's efficacy in maintaining image edges and textures.