Adaptive Context-Aware Generative Adversarial Network for Low-quality Image Enhancement

Low-quality image enhancement methods can effectively improve image quality and details, which have attracted great attention in various fields. However, current methods still face with two issues: (1) They commonly earn a deterministic generation mapping between low-quality and normal images via re...

Full description

Saved in:
Bibliographic Details
Main Authors: Xingyu Pan, Fengling Chen
Format: Article
Language:English
Published: Tamkang University Press 2025-06-01
Series:Journal of Applied Science and Engineering
Subjects:
Online Access:http://jase.tku.edu.tw/articles/jase-202601-29-01-0012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850157298633146368
author Xingyu Pan
Fengling Chen
author_facet Xingyu Pan
Fengling Chen
author_sort Xingyu Pan
collection DOAJ
description Low-quality image enhancement methods can effectively improve image quality and details, which have attracted great attention in various fields. However, current methods still face with two issues: (1) They commonly earn a deterministic generation mapping between low-quality and normal images via relying on pixel-level reconstruction, leading to improper brightness and noise in the enhancing process. (2) They use only one type of generative model, either explicit or implicit, which limits flexibility and efficiency of models. To this end, a novel flow-based generative adversarial network with dual attention (FGAN-DA) is devised for data generation. Specifically, FGAN-DA constructs a hybrid generative model via combining explicit and implicit components within the GAN architecture, which effectively alleviates detail blurred and singularity caused by sole generation modeling. FGAN-DA comprises the dual attention feature extraction, invertible flow generation network, the Markov discriminant network. The three modules seamlessly collaborate in enhancing images with good perceptual quality, which effectively boosts the performance of FGAN-DA. Finally, quantitative metrics and visual quality evaluations demonstrate that FGAN-DA sets a new baseline in can generate images with good perceptual quality.
format Article
id doaj-art-d707f82750bc4788bc3b562ec68c4f59
institution OA Journals
issn 2708-9967
2708-9975
language English
publishDate 2025-06-01
publisher Tamkang University Press
record_format Article
series Journal of Applied Science and Engineering
spelling doaj-art-d707f82750bc4788bc3b562ec68c4f592025-08-20T02:24:13ZengTamkang University PressJournal of Applied Science and Engineering2708-99672708-99752025-06-0129112112810.6180/jase.202601_29(1).0012Adaptive Context-Aware Generative Adversarial Network for Low-quality Image EnhancementXingyu Pan0Fengling Chen1School of Electronic and Electrical Engineering, Zhengzhou University of Science and Technology, Zhengzhou, 450064, ChinaZhengzhou Electric Power College, Zhengzhou, 450003, ChinaLow-quality image enhancement methods can effectively improve image quality and details, which have attracted great attention in various fields. However, current methods still face with two issues: (1) They commonly earn a deterministic generation mapping between low-quality and normal images via relying on pixel-level reconstruction, leading to improper brightness and noise in the enhancing process. (2) They use only one type of generative model, either explicit or implicit, which limits flexibility and efficiency of models. To this end, a novel flow-based generative adversarial network with dual attention (FGAN-DA) is devised for data generation. Specifically, FGAN-DA constructs a hybrid generative model via combining explicit and implicit components within the GAN architecture, which effectively alleviates detail blurred and singularity caused by sole generation modeling. FGAN-DA comprises the dual attention feature extraction, invertible flow generation network, the Markov discriminant network. The three modules seamlessly collaborate in enhancing images with good perceptual quality, which effectively boosts the performance of FGAN-DA. Finally, quantitative metrics and visual quality evaluations demonstrate that FGAN-DA sets a new baseline in can generate images with good perceptual quality.http://jase.tku.edu.tw/articles/jase-202601-29-01-0012data generationdual attentionflow generative network
spellingShingle Xingyu Pan
Fengling Chen
Adaptive Context-Aware Generative Adversarial Network for Low-quality Image Enhancement
Journal of Applied Science and Engineering
data generation
dual attention
flow generative network
title Adaptive Context-Aware Generative Adversarial Network for Low-quality Image Enhancement
title_full Adaptive Context-Aware Generative Adversarial Network for Low-quality Image Enhancement
title_fullStr Adaptive Context-Aware Generative Adversarial Network for Low-quality Image Enhancement
title_full_unstemmed Adaptive Context-Aware Generative Adversarial Network for Low-quality Image Enhancement
title_short Adaptive Context-Aware Generative Adversarial Network for Low-quality Image Enhancement
title_sort adaptive context aware generative adversarial network for low quality image enhancement
topic data generation
dual attention
flow generative network
url http://jase.tku.edu.tw/articles/jase-202601-29-01-0012
work_keys_str_mv AT xingyupan adaptivecontextawaregenerativeadversarialnetworkforlowqualityimageenhancement
AT fenglingchen adaptivecontextawaregenerativeadversarialnetworkforlowqualityimageenhancement