LABFNet: A Restoration Network Guided by the LAB Colour Space and Frequency-Domain Constraints
Journal of Imaging · 22.07.2026 · 12 (7) · 332
DOI: 10.3390/jimaging12070332 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 22.07.2026. Verfasst von Yaqian Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Communication, Hainan University, Haikou 570028, China. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The innovation platform for Academinicians of Hainan Province, innovation platform for Academinicians of Hainan Province.
Abstract (Originalsprache)
In the restoration of mural images with rich colour information and complex texture structures, existing techniques typically extract the spatial-domain features in the Red–Green–Blue (RGB) colour space. However, the three RGB channels are physically decoupled without unified perceptual colour correlation constraints, which often leads to noticeable colour deviation in damaged regions with large colour variations. In addition, restoring both high-frequency texture details and low-frequency global structures in a mixed-frequency spatial domain can create conflicts between frequencies, making it difficult to generate realistic high-frequency details. To address these issues, we propose the laboratory frequency network (LABFNet), a restoration network guided by the laboratory (LAB) colour space and frequency-domain constraints. Our model has two key improvements: (1) it incorporates colour parameters from the LAB space to model colour loss in murals, and (2) it decomposes the image into low- and high-frequency components and enforces frequency consistency during restoration. In the Dunhuang 20–40% mask-ratio setting, the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) improved by 1.58% and 0.27%, respectively, while the Mean Absolute Error (MAE), Learned Perceptual Image Patch Similarity (LPIPS) and CIEDE2000 decreased by 5.87%, 6.5%, and 21.65%, respectively. Experimental results on benchmark datasets show that LABFNet reduces colour deviation and structural defects.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information and Communication, Hainan University, Haikou 570028, China.
- School of Electronic Science and Engineering, Hainan University, Haikou 570028, China.
- School of Information and Communication Engineering, North University of China, Taiyuan 030051, China.
- Algorithm Department, Xi'an Jiaying Intelligent Technology Co., Ltd., Xi'an 710000, China.
ORCID-Profile: Guanjun Wang
Förderung
- The innovation platform for Academinicians of Hainan Province
- innovation platform for Academinicians of Hainan Province
Zitieren
APA
Zhang, Y., Wang, G., Zhang, Q., & Zhou, B. (2026). LABFNet: A Restoration Network Guided by the LAB Colour Space and Frequency-Domain Constraints. Journal of Imaging, 12(7), 332. https://doi.org/10.3390/jimaging12070332
Vancouver
Zhang Y, Wang G, Zhang Q, Zhou B. LABFNet: A Restoration Network Guided by the LAB Colour Space and Frequency-Domain Constraints. Journal of Imaging. 2026;12(7):332. doi:10.3390/jimaging12070332
BibTeX
@article{Zhang2026,
author = {Zhang, Yaqian and Wang, Guanjun and Zhang, Quan and Zhou, Bochao},
title = {LABFNet: A Restoration Network Guided by the LAB Colour Space and Frequency-Domain Constraints},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {7},
pages = {332},
doi = {10.3390/jimaging12070332}
}
EUVIMED