Adaptive Filtering-Based Demoiréing Method

Se Ho Lee

doi:10.7840/kics.2025.50.8.1192

Adaptive Filtering-Based Demoiréing Method

Se Ho Lee^*

^*Corresponding author for this work

Research output: Contribution to journal › Journal article › peer-review

Abstract

This paper proposes a frequency-aware adaptive filtering method for image demoiréing. The method uses a multi-scale architecture that dynamically adjusts filter weights according to the frequency characteristics of the input image. The backbone network predicts filter weights, and the encoder-decoder pipeline restores clean images. Experimental results show that the proposed method outperforms existing approaches.

Original language	English
Pages (from-to)	1192-1195
Number of pages	4
Journal	Journal of Korean Institute of Communications and Information Sciences
Volume	50
Issue number	8
DOIs	https://doi.org/10.7840/kics.2025.50.8.1192
State	Published - 2025.08

Keywords

adaptive filter
analysis
Demoiréing
frequency

Access to Document

10.7840/kics.2025.50.8.1192

Cite this

@article{e631bcd8b5504997b1907d721e3fdb2d,

title = "Adaptive Filtering-Based Demoir{\'e}ing Method",

abstract = "This paper proposes a frequency-aware adaptive filtering method for image demoir{\'e}ing. The method uses a multi-scale architecture that dynamically adjusts filter weights according to the frequency characteristics of the input image. The backbone network predicts filter weights, and the encoder-decoder pipeline restores clean images. Experimental results show that the proposed method outperforms existing approaches.",

keywords = "adaptive filter, analysis, Demoir{\'e}ing, frequency",

author = "Lee, \{Se Ho\}",

year = "2025",

month = aug,

doi = "10.7840/kics.2025.50.8.1192",

language = "English",

volume = "50",

pages = "1192--1195",

journal = "Journal of Korean Institute of Communications and Information Sciences",

issn = "1226-4717",

number = "8",

}

TY - JOUR

T1 - Adaptive Filtering-Based Demoiréing Method

AU - Lee, Se Ho

PY - 2025/8

Y1 - 2025/8

N2 - This paper proposes a frequency-aware adaptive filtering method for image demoiréing. The method uses a multi-scale architecture that dynamically adjusts filter weights according to the frequency characteristics of the input image. The backbone network predicts filter weights, and the encoder-decoder pipeline restores clean images. Experimental results show that the proposed method outperforms existing approaches.

AB - This paper proposes a frequency-aware adaptive filtering method for image demoiréing. The method uses a multi-scale architecture that dynamically adjusts filter weights according to the frequency characteristics of the input image. The backbone network predicts filter weights, and the encoder-decoder pipeline restores clean images. Experimental results show that the proposed method outperforms existing approaches.

KW - adaptive filter

KW - analysis

KW - Demoiréing

KW - frequency

UR - https://www.scopus.com/pages/publications/105014799376

U2 - 10.7840/kics.2025.50.8.1192

DO - 10.7840/kics.2025.50.8.1192

M3 - Journal article

AN - SCOPUS:105014799376

SN - 1226-4717

VL - 50

SP - 1192

EP - 1195

JO - Journal of Korean Institute of Communications and Information Sciences

JF - Journal of Korean Institute of Communications and Information Sciences

IS - 8

ER -

Adaptive Filtering-Based Demoiréing Method

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this