Lightweight single image super-resolution with attentive residual refinement network

Qin, Jinghui1; Zhang, Rumin2

2022-08-21

10.1016/j.neucom.2022.05.066

NEUROCOMPUTING   Impact Factor & Quartile

0925-2312

1872-8286

In recent years, deep convolutional neural network (CNN) based single image super-resolution (SISR) methods have been demonstrated impressive performance in terms of quantitative metrics and visual effects. Most CNN-based SISR methods can learn the complex non-linear mapping between lowresolution (LR) images and their corresponding high-resolution (HR) images due to the powerful representation capabilities of deep convolutional neural networks. However, as the depth and width of the SISR networks increase, the parameters of SISR networks will increase dramatically, leading to huge computational cost and large memory consumption, making them impractical in real-world applications. To attack the above issues, we propose an accurate and lightweight deep convolutional neural network, named Attentive Residual Refinement Network (ARRFN), to recover the high-resolution image from the original low-resolution image directly for SISR. In general, our proposed ARRFN consists of three parts, a feature extraction block, a stack of attentive residual refinement blocks (ARRFB), and a multi-scale separable upscaling module (MSSU), respectively. Specifically, our ARRFB consists of two branches, a regular residual learning branch and an attentive residual refinement branch. The former conducts regular residual learning by two residual blocks while the latter refines the residual information from the two residual blocks of the former branch with an attentive residual mechanism to further enhance the representation capabilities of the network. Furthermore, a multi-scale separable upsampling module (MSSU) is proposed to replace the regular upsampling operation for better SR results. Extensive experiments on several standard benchmarks show that the proposed method outperforms state-of-the-art SR methods in terms of quantitative metrics, visual quality, memory footprint, and inference time. (c) 2022 Elsevier B.V. All rights reserved.

Single image super-resolution Lightweight network Attentive residual refinement Multi-scale separable upscaling

SCI ; EI

English

Corresponding

National Key R&D Program of the Ministry of Science and Technology[2021YFE0204000] ; National Natural Science Foundation of Guang-dong Province[2022A1515011835] ; China Postdoctoral Science Foundation[2021M703687]

Computer Science

Computer Science, Artificial Intelligence

WOS:000822674600001

ELSEVIER

COMPUTER SCIENCE

Web of Science

1.Sun Yat sen Univ, Sch Comp Sci & Engn, Guangzhou 510006, Peoples R China
2.Southern Univ Sci & Technol, Sch Microelect, Shenzhen 518055, Peoples R China

Qin, Jinghui,Zhang, Rumin. Lightweight single image super-resolution with attentive residual refinement network[J]. NEUROCOMPUTING,2022,500.

Qin, Jinghui,&Zhang, Rumin.(2022).Lightweight single image super-resolution with attentive residual refinement network.NEUROCOMPUTING,500.

Qin, Jinghui,et al."Lightweight single image super-resolution with attentive residual refinement network".NEUROCOMPUTING 500(2022).