Single Image Super Resolution using Deep Learning: A Survey
Keywords:
Image Super Resolution, SRCNN (Super Resolution Convolution neural network), SRGAN(Super Resolution Generative Adversarial Network )Abstract
Single image super-resolution, which is used to restore high-resolution image from a single lowresolution image, is a difficult challenging problem in computer field. In recent times, dominant deep learning
algorithms have been applied to Single image super resolution and have shown an highly efficient performance. In this
paper, we surveyed deep learning-based super resolution method known as a super resolution convolutional neural
network (SRCNN) that takes the low-resolution image as the input and outputs the high-resolution one. SRCNN has a
non-complex structure yet provides high quality and fast speed. We get quick results for practical online usage. Hence,
survey is carried out on different networks like Generative Adversarial Networks (GAN) and Convolutional Neural
Network comparison between quality and speed.
