Network architecture for single image super‐resolution: A comprehensive review and comparison

• Published in: IET image processing 2024-07, Vol.18 (9), p.2215-2243
• Main Authors: Zhang, Zhicun, Han, Yu, Zhu, Linlin, Xi, Xiaoqi, Li, Lei, Liu, Mengnan, Tan, Siyu, Yan, Bin
• Format: Article
• Language: English
• Subjects: computer vision; convolutional neural nets; image enhancement; image reconstruction; image resolution; image restoration; neural net architecture; neural nets
• ISSN: 1751-9659; 1751-9667
• DOI: 10.1049/ipr2.13100

Single image super‐resolution (SISR) is a promising research direction in computer vision and image processing for improving the visual perception of low‐quality images. In recent years, deep learning algorithms have driven tremendous development in SR, and SR methods based on various network architectures have significantly improved the quality of reconstructed images. Although there has been a large amount of reviews focusing on SISR, few studies have focused specifically on network architectures for SISR. This paper aims to provide a systematic overview of the design ideas of SISR using multiple architectures, including Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN), Transformer, and Diffusion model. In addition, an experimental analysis and comparison of state‐of‐the‐art SR algorithms have been performed on publicly available quantitative and qualitative datasets. Finally, some future directions are discussed that may help other community researchers. This paper aims to provide a systematic overview of the design ideas of SISR using multiple architectures, including Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN), Transformer, and Diffusion. In addition, we have performed an experimental analysis and comparison of state‐of‐the‐art SR algorithms on publicly available quantitative and qualitative datasets. Finally, we discuss some future directions that may help other community researchers.