Image Super-resolution with An Enhanced Group Convolutional Neural Network

TL;DR

This paper introduces ESRGCNN, a shallow yet effective CNN model for image super-resolution that fuses deep and wide features, enhancing accuracy and efficiency compared to deeper networks.

Contribution

The paper proposes a novel shallow CNN architecture with feature fusion and signal enhancement for improved super-resolution performance.

Findings

ESRGCNN outperforms state-of-the-art methods in accuracy and speed.

The model achieves better image quality and visual effects.

It maintains low complexity with competitive results.

Abstract

CNNs with strong learning abilities are widely chosen to resolve super-resolution problem. However, CNNs depend on deeper network architectures to improve performance of image super-resolution, which may increase computational cost in general. In this paper, we present an enhanced super-resolution group CNN (ESRGCNN) with a shallow architecture by fully fusing deep and wide channel features to extract more accurate low-frequency information in terms of correlations of different channels in single image super-resolution (SISR). Also, a signal enhancement operation in the ESRGCNN is useful to inherit more long-distance contextual information for resolving long-term dependency. An adaptive up-sampling operation is gathered into a CNN to obtain an image super-resolution model with low-resolution images of different sizes. Extensive experiments report that our ESRGCNN surpasses the state-of-the-arts in terms of SISR performance, complexity, execution speed, image quality evaluation and visual effect in SISR. Code is found at https://github.com/hellloxiaotian/ESRGCNN.