Deeply Recursive Low- and High-Frequency Fusing Networks for Single Image Super-Resolution

Abstract

With the development of researches on single image super-resolution (SISR) based on convolutional neural networks (CNN), the quality of recovered images has been remarkably promoted. Since then, many deep learning-based models have been proposed, which have outperformed the traditional SISR algorithms. According to the results of extensive experiments, the feature representations of the model can be enhanced by increasing the depth and width of the network, which can ultimately improve the image reconstruction quality. However, a larger network generally consumes more computational and memory resources, making it difficult to train the network and increasing the prediction time. In view of the above problems, a novel deeply-recursive low- and high-frequency fusing network (DRFFN) for SISR tasks is proposed in this paper, which adopts the structure of parallel branches to extract the low- and high-frequency information of the image, respectively. The different complexities of the branches can reflect the frequency characteristic of the diverse image information. Moreover, an effective channel-wise attention mechanism based on variance (VCA) is designed to make the information distribution of each feature map more reasonably with different variances. Owing to model structure (i.e., cascading recursive learning of recursive units), DRFFN and DRFFN-L are very compact, where the weights are shared by all convolutional recursions. Comprehensive benchmark evaluations in standard benchmark datasets well demonstrate that DRFFN outperforms the most existing models and has achieved competitive, quantitative, and visual results.

Frequency-Based Enhancement Network for Efficient Super-Resolution

“…Later, Haris et al [17] proposed a method to refine high-frequency texture details with a series of up and downsampling layers that are densely connected with each other to combine HR images from multiple depths in the network. More recently, Qiu et al [46] and Yang and Lu [60] proposed multi-branch architectures. In these methods, one branch is responsible for capturing high-frequency features such as texture and edge, and another is to learn low-frequency features such as image outline and contour.…”

“…However, as SR networks are so diverse, the attention module is usually designed solely for a specific network structure [55]. Recently, various SR methods such as multi-branch networks [33,60] and progressive reconstruction methods [35,69] mainly focus on refining the highfrequency texture details. Although these methods delivered impressive results, they demand substantial memory and computational resources.…”

Survey on CNN based super resolution methods

“…Despite the fact that the processing of the developed bicubic LR images may be complicated with the standard gradient approach due to burst/fade gradients and increased expulsion between parameters and layers, the results were PSNR = 37.63, SSIM = 0.9588 and PSNR = 33.66, SSIM = 0.9299. Yang & Lu, (2020) proposed in 2020 to improve model representations by increasing the grid's depth and width, which would result in greater image rebuilding quality.…”

Fault Diagnosis Method for Rolling Mill Multi Row Bearings Based on AMVMD-MC1DCNN under Unbalanced Dataset

“…Convolutional Neural Networks (CNNs) have had significant achievements in the field of image recognition and have become a research hotspot in deep learning [ 19 ]. CNN has the function of automatic feature extraction and pattern recognition, which can realize the fault identification of equipment by inputting vibration signal.…”