bibtype	J - Journal Article
ARLID	0641516
utime	20260123171914.5
mtime	20251114235959.9
WOS	001619816300001
DOI	10.1016/j.mlwa.2025.100772
title (primary) (eng)	Model-based multispectral texture inpainting and denoising
specification	page_count 11 s. media_type P
serial	ARLID cav_un_epca*0641515 ISSN Machine Learning with Applications title Machine Learning with Applications volume_id 22 publisher name Elsevier
keyword	Texture inpainting
keyword	3D Gaussian mixture model
keyword	texture restoration
keyword	3D Gaussian causal simultaneous autoregressive model
keyword	texture synthesis
keyword	multispectral texture modeling
author (primary)	ARLID cav_un_auth*0101093 name1 Haindl name2 Michal institution UTIA-B full_dept (cz) Rozpoznávání obrazu full_dept (eng) Department of Pattern Recognition department (cz) RO department (eng) RO full_dept Department of Pattern Recognition garant K fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author	ARLID cav_un_auth*0101100 name1 Havlíček name2 Vojtěch institution UTIA-B full_dept (cz) Rozpoznávání obrazu full_dept Department of Pattern Recognition department (cz) RO department RO fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author	ARLID cav_un_auth*0101239 name1 Žid name2 Pavel institution UTIA-B full_dept (cz) Rozpoznávání obrazu full_dept Department of Pattern Recognition department (cz) RO department RO full_dept Department of Pattern Recognition fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source	url https://library.utia.cas.cz/separaty/2025/RO/haindl-0641516.pdf
cas_special	abstract (eng) 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. result_subspec WOS RIV IN FORD0 20000 FORD1 20200 FORD2 20205 reportyear 2026 num_of_auth 3 inst_support RVO:67985556 permalink https://hdl.handle.net/11104/0371972 confidential S article_num 100772 mrcbC91 A mrcbT16-j 1.343 arlyear 2025 mrcbU14 SCOPUS mrcbU24 PUBMED mrcbU34 001619816300001 WOS mrcbU63 cav_un_epca*0641515 Machine Learning with Applications Roč. 22 č. 1 2025 2666-8270 Elsevier