Brief Survey of Single Image Super-Resolution Reconstruction Based on Deep Learning Approaches

• Published in: Sensing and imaging Vol. 21; no. 1
• Main Authors: Wang, Wei, Hu, Yihui, Luo, Yanhong, Zhang, Tong
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.12.2020; Springer Nature B.V
• Subjects: Artificial neural networks; Deep learning; Electrical Engineering; Engineering; Image reconstruction; Image resolution; Imaging; Machine learning; Mapping; Microwaves; Neural networks; Overview; Radiology; RF and Optical Engineering; Summary paper; Dense network; Single image super-resolution (SISR) reconstruction; Convolutional neural network (CNN); Residual learning; Generative adversarial networks (GANs)
• ISSN: 1557-2064; 1557-2072
• DOI: 10.1007/s11220-020-00285-4

With the presentation of super-resolution convolutional neural network, deep learning approach was applied to image super-resolution reconstruction for the first time. By using convolutional neural network, the deep learning approaches can directly learn the mapping relationship between the low-resolution image and high-resolution image, and have achieved better reconstruction effects than the traditional image super-resolution reconstruction methods. Subsequently, a series of improved deep learning approaches have been proposed, and the reconstruction effects have been improved continuously. This paper systematically summa rizes the image super-resolution reconstruction approaches based on deep learning, analyzes the characteristics of different models, and compares the main deep learning models based on the experiments. Furthermore, based on deep learning model, the future research directions of the image super-resolution reconstruction methods based on deep learning models are reasonably predicted.