Gated RedNet for image denoising
PeerJ Computer Science · 27.05.2026 · 12 · e3900
DOI: 10.7717/peerj-cs.3900 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 27.05.2026. Verfasst von Huibin Zhang und 4 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanxi Province Applied Basic Research Program, China.
Abstract (Originalsprache)
Deep learning has garnered widespread attention in the computer vision field, particularly for image denoising tasks. While Transformer-based models currently represent the state-of-the-art in denoising performance, this work investigates whether the architecture based on convolutional neural networks (CNN) can achieve comparable results. We propose GatedRedNet, a novel three-layer encoder-decoder network designed for image denoising. To enhance network depth while maintaining efficiency, GatedRedNet incorporates attention mechanisms within its residual blocks. Specifically, we incorporate the Efficient Channel Attention (ECA) module within all residual blocks, enabling effective recovery of edge and texture details with minimal computational overhead. To further improve global feature learning, we introduce a learnable gating factor at the encoder-decoder fusion stage, dynamically adjusting the weight ratio between their feature maps. These designs enable GatedRedNet to better capture local texture features while maintaining robust denoising capabilities. We evaluate GatedRedNet extensively on multiple benchmark datasets, demonstrating denoising performance comparable to state-of-the-art Transformer-based models and even surpassing them in certain aspects. Our results suggest that well-designed CNN architectures remain competitive in image denoising, offering an efficient alternative to Transformer.
Förderung
- Shanxi Province Applied Basic Research Program, China
Zitieren
APA
Zhang, H., Feng, L., Li, J., Zhou, F., & Zhang, G. (2026). Gated RedNet for image denoising. PeerJ Computer Science, 12, e3900. https://doi.org/10.7717/peerj-cs.3900
Vancouver
Zhang H, Feng L, Li J, Zhou F, Zhang G. Gated RedNet for image denoising. PeerJ Computer Science. 2026;12:e3900. doi:10.7717/peerj-cs.3900
BibTeX
@article{Zhang2026,
author = {Zhang, Huibin and Feng, Liping and Li, Jing and Zhou, Fang and Zhang, Guorong},
title = {Gated RedNet for image denoising},
journal = {PeerJ Computer Science},
year = {2026},
volume = {12},
pages = {e3900},
doi = {10.7717/peerj-cs.3900}
}
EUVIMED