Effects Of Normalised SSIM Loss On Super-Resolution Tasks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60460709%3A41110%2F25%3A101814" target="_blank" >RIV/60460709:41110/25:101814 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.techscience.com/CMES/v143n3/62840" target="_blank" >https://www.techscience.com/CMES/v143n3/62840</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.32604/cmes.2025.066025" target="_blank" >10.32604/cmes.2025.066025</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Effects Of Normalised SSIM Loss On Super-Resolution Tasks

Popis výsledku v původním jazyce

This study proposes a new component of the composite loss function minimised during training of the Super-Resolution (SR) algorithms – the normalised structural similarity index loss L_SSIM_N, which has the potential to improve the natural appearance of reconstructed images. Deep learning-based super-resolution (SR) algorithms reconstruct high-resolution images from low-resolution inputs, offering a practical means to enhance image quality without requiring superior imaging hardware, which is particularly important in medical applications where diagnostic accuracy is critical. Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity, visual artefacts may persist, making the design of the loss function during training essential for ensuring reliable and naturalistic image reconstruction. Our research shows on two models – SR and Invertible Rescaling Neural Network (IRN) – trained on multiple benchmark datasets that the function L_SSIM_N significantly contributes to the visual quality, preserving the structural fidelity on the reference datasets. The quantitative analysis of results while incorporating L_SSIM_N shows that including this loss function component has a mean 2.88 % impact on the improvement of the final structural similarity of the reconstructed images in the validation set, in comparison to leaving it out and 0.218% in comparison when this component is non-normalised.

Název v anglickém jazyce

Effects Of Normalised SSIM Loss On Super-Resolution Tasks

Popis výsledku anglicky

This study proposes a new component of the composite loss function minimised during training of the Super-Resolution (SR) algorithms – the normalised structural similarity index loss L_SSIM_N, which has the potential to improve the natural appearance of reconstructed images. Deep learning-based super-resolution (SR) algorithms reconstruct high-resolution images from low-resolution inputs, offering a practical means to enhance image quality without requiring superior imaging hardware, which is particularly important in medical applications where diagnostic accuracy is critical. Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity, visual artefacts may persist, making the design of the loss function during training essential for ensuring reliable and naturalistic image reconstruction. Our research shows on two models – SR and Invertible Rescaling Neural Network (IRN) – trained on multiple benchmark datasets that the function L_SSIM_N significantly contributes to the visual quality, preserving the structural fidelity on the reference datasets. The quantitative analysis of results while incorporating L_SSIM_N shows that including this loss function component has a mean 2.88 % impact on the improvement of the final structural similarity of the reconstructed images in the validation set, in comparison to leaving it out and 0.218% in comparison when this component is non-normalised.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

CMES - Computer Modeling in Engineering and Sciences

ISSN

1526-1492

e-ISSN

1526-1492

Svazek periodika

143

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

21

Strana od-do

3329-3349

Kód UT WoS článku

001527987300001

EID výsledku v databázi Scopus

2-s2.0-105010567210