Fidelity-preserving Learning-Based Image Compression: Loss Function and Subjective Evaluation Methodology

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mohammadi, Shima, Wu, Yaojun, Ascenso, João
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911802739130368
author Mohammadi, Shima
Wu, Yaojun
Ascenso, João
author_facet Mohammadi, Shima
Wu, Yaojun
Ascenso, João
contents Learning-based image compression methods have emerged as state-of-the-art, showcasing higher performance compared to conventional compression solutions. These data-driven approaches aim to learn the parameters of a neural network model through iterative training on large amounts of data. The optimization process typically involves minimizing the distortion between the decoded and the original ground truth images. This paper focuses on perceptual optimization of learning-based image compression solutions and proposes: i) novel loss function to be used during training and ii) novel subjective test methodology that aims to evaluate the decoded image fidelity. According to experimental results from the subjective test taken with the new methodology, the optimization procedure can enhance image quality for low-rates while offering no advantage for high-rates.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11241
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fidelity-preserving Learning-Based Image Compression: Loss Function and Subjective Evaluation Methodology
Mohammadi, Shima
Wu, Yaojun
Ascenso, João
Multimedia
Learning-based image compression methods have emerged as state-of-the-art, showcasing higher performance compared to conventional compression solutions. These data-driven approaches aim to learn the parameters of a neural network model through iterative training on large amounts of data. The optimization process typically involves minimizing the distortion between the decoded and the original ground truth images. This paper focuses on perceptual optimization of learning-based image compression solutions and proposes: i) novel loss function to be used during training and ii) novel subjective test methodology that aims to evaluate the decoded image fidelity. According to experimental results from the subjective test taken with the new methodology, the optimization procedure can enhance image quality for low-rates while offering no advantage for high-rates.
title Fidelity-preserving Learning-Based Image Compression: Loss Function and Subjective Evaluation Methodology
topic Multimedia
url https://arxiv.org/abs/2403.11241