Implicit neural representation for image demosaicking

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F25%3A00616904" target="_blank" >RIV/67985556:_____/25:00616904 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21340/25:00390510

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S1051200425000442?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S1051200425000442?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.dsp.2025.105022" target="_blank" >10.1016/j.dsp.2025.105022</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Implicit neural representation for image demosaicking

Popis výsledku v původním jazyce

We propose a novel approach to enhance image demosaicking algorithms using implicit neural representations (INR). Our method employs a multi-layer perceptron to encode RGB images, combining original Bayer measurements with an initial estimate from existing demosaicking methods to achieve superior reconstructions. A key innovation is the integration of two loss functions: a Bayer loss for fidelity to sensor data and a complementary loss that regularizes reconstruction using interpolated data from the initial estimate. This combination, along with INR’s inherent ability to capture fine details, enables hig-fidelity reconstructions that incorporate information from both sources. Furthermore, we demonstrate that INR can effectively correct artifacts in state-of-the-art demosaicking methods when input data diverge from the training distribution, such as in cases of noise or blur. This adaptability highlights the transformative potential of INR-based demosaicking, offering a robust solution to this challenging problem.

Název v anglickém jazyce

Implicit neural representation for image demosaicking

Popis výsledku anglicky

We propose a novel approach to enhance image demosaicking algorithms using implicit neural representations (INR). Our method employs a multi-layer perceptron to encode RGB images, combining original Bayer measurements with an initial estimate from existing demosaicking methods to achieve superior reconstructions. A key innovation is the integration of two loss functions: a Bayer loss for fidelity to sensor data and a complementary loss that regularizes reconstruction using interpolated data from the initial estimate. This combination, along with INR’s inherent ability to capture fine details, enables hig-fidelity reconstructions that incorporate information from both sources. Furthermore, we demonstrate that INR can effectively correct artifacts in state-of-the-art demosaicking methods when input data diverge from the training distribution, such as in cases of noise or blur. This adaptability highlights the transformative potential of INR-based demosaicking, offering a robust solution to this challenging problem.

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

<a href="/cs/project/GA25-15933S" target="_blank" >GA25-15933S: Dynamické inverzní problémy v časosběrné mikroskopii</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název periodika

Digital Signal Processing

ISSN

1051-2004

e-ISSN

1095-4333

Svazek periodika

159

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

14

Strana od-do

105022

Kód UT WoS článku

001420733900001

EID výsledku v databázi Scopus

2-s2.0-85216108770