Recent Advances in 2D Image Upscaling: A Comprehensive Review

Image interpolation is the process of transforming a low-resolution image into a higher-resolution image of a different size. The current study analyzes several picture interpolation algorithms, concentrating on their utility and effectiveness in creating higher upscaled images. However, small details are typically lost during upscaling, resulting in unclear images. Polynomial-based, transform domain-based, learning-based, and reconstruction-based interpolation algorithms are explored, as well as their difficulties in keeping fine details. The use of convolutional neural networks (CNN) in deep-learning-based image interpolation methods is highlighted. Image interpolation topics such as processing efficiency and assessment criteria are addressed. The article examines the performance, limitations, and benefits of interpolation algorithms that combine classical and deep-learning-based methods.