This repository contains the results of the subjective tests conducted in the experiment.

Cropped images used in the subjective test

• LBIC-PO: The "LBIC-PO" refers to the learning-based codec with perceptual optimization techniques applied.
• LBIC-CO: The "LBIC-CO" refers to the learning-based codec without any perceptual optimization techniques applied.
• Reference: The uncompressed reference images

The subjective results is available in the preference.csv file.

If you find this repository useful for your research, please use the following.

@INPROCEEDINGS{10402691,
  author={Mohammadi, Shima and Wu, Yaojun and Ascenso, João},
  booktitle={2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)}, 
  title={Fidelity-preserving Learning-Based Image Compression: Loss Function and Subjective Evaluation Methodology}, 
  year={2023},
  volume={},
  number={},
  pages={1-5},
  doi={10.1109/VCIP59821.2023.10402691}}

This work is funded by FCT/MCTES through national funds and when applicable co-funded EU funds under the project DARING with reference PTDC/EEI-COM/7775/2020.