A comprehensive review of image super-resolution metrics: classical and AI-based approaches

Authors

  • Mukhriddin Arabboev Tashkent University of Information Technologies named after Muhammad al-Khwarizmi
  • Shohruh Begmatov Tashkent University of Information Technologies named after Muhammad al-Khwarizmi
  • Mokhirjon Rikhsivoev Tashkent University of Information Technologies named after Muhammad al-Khwarizmi
  • Khabibullo Nosirov Tashkent University of Information Technologies named after Muhammad al-Khwarizmi
  • Saidakmal Saydiakbarov Tashkent University of Information Technologies named after Muhammad al-Khwarizmi

DOI:

https://doi.org/10.21014/actaimeko.v13i1.1679

Keywords:

Image super-resolution, Metrics, LPIPS, FID, IS, MSE, RMSE, SSIM, MS-SSIM, PSNR, AI-based methods

Abstract

Image super-resolution is a process that aims to enhance the quality and resolution of images using various techniques and algorithms. The process aims to reconstruct a high-resolution image from a given low-resolution input. To determine the effectiveness of these algorithms, it's crucial to evaluate those using specific metrics. In this paper, we take a closer look at the most commonly used image super-resolution metrics, including classical approaches like Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Peak Signal to Noise Ratio (PSNR), and Structural Similarity Index (SSIM). We also discuss advanced metrics like Learned Perceptual Image Patch Similarity (LPIPS), Fréchet Inception Distance (FID), Inception Score (IS), and Multi-Scale Structural Similarity Index (MS-SSIM). Furthermore, we provide an overview of classical and AI-based super-resolution techniques and methods. Finally, we discuss potential challenges and future research directions in the field and present our experimental results by applying image super-resolution metrics. In the result and discussion section, we have practiced some given metrics and proposed our image super-resolution results.

Downloads

Published

2024-03-12

Issue

Vol. 13 No. 1 (2024)

Section

Research Papers

License

Copyright (c) 2024 Mukhriddin Arabboev, Shohruh Begmatov, Mokhirjon Rikhsivoev, Khabibullo Nosirov, Saidakmal Saydiakbarov

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under the CC BY 4.0, Creative Commons Attribution 4.0 International License.

Users are free to

  • share, i.e. copy and redistribute the material in any medium or format for any purpose, even commercially;
  • adapt, i.e. remix, transform, and build upon the material for any purpose, even commercially.

At the same time, the user must give appropriate credit, provide a link to the license, and indicate if changes were made.
Additional information about the license can be found at: https://creativecommons.org/licenses/by/4.0/.

Authors are

  • able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  • permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).