With the increase in the resolution supported by displays and screens, the consumption of high-quality content such as 4 K resolution videos and images is increasing rapidly. To address the need for increasing fidelity, image super-resolution has been proposed to increase the resolution of images artificially. Image super-resolution produces a high-resolution image from a low-resolution image. The domain has seen outstanding growth in recent years due to the introduction of deep learning techniques. In this paper, we aim to give a quick review of the various approaches used, their merits and what inspired them. The highlight of this work is the inculcation of recently introduced layers and the review of non-traditional approaches such as the importance of the receptive field and perceptually oriented metrics. We also provide directions and recommendations to the community to extend the research done in this domain.
CITATION STYLE
Chauhan, K., Patel, H., Dave, R., Bhatia, J., & Kumhar, M. (2020). Advances in Single Image Super-Resolution: A Deep Learning Perspective. In Lecture Notes in Networks and Systems (Vol. 121, pp. 443–455). Springer. https://doi.org/10.1007/978-981-15-3369-3_34
Mendeley helps you to discover research relevant for your work.