A review of single image super-resolution reconstruction based on deep learning

Single image super-resolution (SISR) is an important research field in computer vision, the purpose of which is to recover clear, high-resolution (HR) images from low-resolution (LR) images. With the rapid developments in deep learning theory and technology, deep learning has been introduced into the field of image super-resolution (SR), and has achieved results far beyond traditional methods in many domains. This paper summarizes current image SR algorithms based on deep learning. Firstly, the mainstream frameworks, loss functions, and datasets used for SISR are introduced in detail. Then, the SISR algorithm based on deep learning is explored using three models: a convolutional neural network (CNN), a generative adversarial network (GAN), and a transformer. Next, the evaluation indices used for SR are introduced, and the reconstruction results from various algorithms based on deep learning are compared. Finally, future trends in research on image SR algorithms based on deep learning are summarized.