Single-Image Super-Resolution Reconstruction based on the Differences of Neighboring Pixels

TL;DR

This paper introduces a novel approach for single-image super-resolution that leverages the differences between neighboring pixels to improve CNN regularization, capturing local spatial structure more effectively.

Contribution

It proposes using neighbor pixel differences to regularize CNN training, emphasizing local spatial relationships often overlooked in existing methods.

Findings

Outperforms state-of-the-art methods in benchmarks

Improves preservation of local spatial structures

Enhances quantitative and qualitative super-resolution results

Abstract

The deep learning technique was used to increase the performance of single image super-resolution (SISR). However, most existing CNN-based SISR approaches primarily focus on establishing deeper or larger networks to extract more significant high-level features. Usually, the pixel-level loss between the target high-resolution image and the estimated image is used, but the neighbor relations between pixels in the image are seldom used. On the other hand, according to observations, a pixel's neighbor relationship contains rich information about the spatial structure, local context, and structural knowledge. Based on this fact, in this paper, we utilize pixel's neighbor relationships in a different perspective, and we propose the differences of neighboring pixels to regularize the CNN by constructing a graph from the estimated image and the ground-truth image. The proposed method outperforms the state-of-the-art methods in terms of quantitative and qualitative evaluation of the benchmark datasets. Keywords: Super-resolution, Convolutional Neural Networks, Deep Learning