Model-based multispectral texture inpainting and denoising

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F25%3A00641516" target="_blank" >RIV/67985556:_____/25:00641516 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S2666827025001550?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S2666827025001550?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.mlwa.2025.100772" target="_blank" >10.1016/j.mlwa.2025.100772</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Model-based multispectral texture inpainting and denoising

Popis výsledku v původním jazyce

Visual texture inpainting and denoising aim not necessarily to recover the exact pixel-wise correspondence of the original, often unobservable, texture, but rather to reconstruct a texture that is visually indistinguishable from the original. This objective differs from standard image restoration goals and therefore may require fundamentally different restoration techniques. This work presents two multispectral texture restoration methods capable of simultaneously reducing additive Gaussian or Poisson noise and inpainting missing textural regions without visible seams or repetitions. Both methods rely on descriptive three-dimensional statistical spatial models. The first method employs a complex three-dimensional spatial Gaussian mixture model, particularly suited for regular or near-regular textures. The second method uses a causal simultaneous autoregressive model, which is more appropriate for random textures or scenarios with limited training data. Importantly, both models are inherently multispectral, enabling the restoration of even hyperspectral textures. As such, they avoid the spectral quality compromises typically encountered in many alternative approaches. The Gaussian and Poisson noise reduction achieved by the proposed method is compared with four alternative approaches, showing an average improvement of 1%–16% across the spectral range while avoiding the blurring artifacts observed in some of the other methods.

Název v anglickém jazyce

Model-based multispectral texture inpainting and denoising

Popis výsledku anglicky

Visual texture inpainting and denoising aim not necessarily to recover the exact pixel-wise correspondence of the original, often unobservable, texture, but rather to reconstruct a texture that is visually indistinguishable from the original. This objective differs from standard image restoration goals and therefore may require fundamentally different restoration techniques. This work presents two multispectral texture restoration methods capable of simultaneously reducing additive Gaussian or Poisson noise and inpainting missing textural regions without visible seams or repetitions. Both methods rely on descriptive three-dimensional statistical spatial models. The first method employs a complex three-dimensional spatial Gaussian mixture model, particularly suited for regular or near-regular textures. The second method uses a causal simultaneous autoregressive model, which is more appropriate for random textures or scenarios with limited training data. Importantly, both models are inherently multispectral, enabling the restoration of even hyperspectral textures. As such, they avoid the spectral quality compromises typically encountered in many alternative approaches. The Gaussian and Poisson noise reduction achieved by the proposed method is compared with four alternative approaches, showing an average improvement of 1%–16% across the spectral range while avoiding the blurring artifacts observed in some of the other methods.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

—

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

Machine Learning with Applications

ISSN

2666-8270

e-ISSN

2666-8270

Svazek periodika

22

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

11

Strana od-do

100772

Kód UT WoS článku

001619816300001

EID výsledku v databázi Scopus

2-s2.0-105027917659