Skip to content

Comparative Study of Traditional and AI-based Image Compression Methods

Notifications You must be signed in to change notification settings

amir-not2005/AI-vs-Traditional-ImageCompression

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

AI-vs-Traditional-ImageCompression

Comparative Study of Traditional and AI-based Image Compression Methods

This repository contains a research paper comparing traditional image compression techniques with AI-based models, focusing on compression efficiency and image quality.

Overview

The paper evaluates two traditional methods, JPEG and HEIF, alongside three AI-based models from the CompressAI library:

  • cheng2020-anchor
  • mbt2018-mean
  • bmshj2018-hyperprior

The goal is to evaluate how well AI-driven models can perform against traditional approaches in terms of compression ratio and image quality (measured using metrics like PSNR and SSIM). These metrics help compare the efficiency and quality retention of both traditional and AI-based compression methods.

Example results

image Screenshot 2024-10-02 at 17 27 43

Darias, A. (2023, August 4). Desmond Bane is making good progress in his rehabilitation. nbamaniacs. https://www.nbamaniacs.com/en/news/Desmond-Bane-is-making-good-progress-in-his-rehabilitation/

About

Comparative Study of Traditional and AI-based Image Compression Methods

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published