Multi-stage cross-transformer-based CNN for image denoising
The Computer Journal · 15.11.2026 · 69 (11) · 1794-1815
DOI: 10.1093/comjnl/bxag059 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Computer Journal, online erschienen am 20.06.2026. Verfasst von Cong Thang Pham und 1 weiteren Autor:innen. Die Arbeit nennt 80 Literaturangaben. Gefördert von: University of Danang – University of Science and Technology.
Abstract (Originalsprache)
Deep convolutional neural networks have shown exceptional performance in eliminating spatially invariant noise, such as synthetic noise, from images. However, their effectiveness diminishes with real-world images, often requiring complex, multi-stage architectures. To overcome this challenge and improve the practical applicability of denoising algorithms, this paper introduces a novel model called cross-Transformer denoising convolutional neural network (CTCNet). CTCNet is built upon three core components: consecutive blocks (CB), parallel blocks (PB), and a filtering block (FB). The CB employs a ConvNeXt block to extract essential structural information, ensuring effective noise removal. To minimize information loss, PB integrates three heterogeneous networks to support multi-level feature interaction, enhancing adaptability to complex real-world scenes. Transformer blocks are strategically embedded within both CB and PB to further boost performance. A fusion Module aggregates outputs from the sub-blocks, promoting inter-channel feature interaction. Additionally, this study introduces Dual multilayer perceptron (Dual MLP) and Cross-Dual multilayer perceptron (Cross-Dual MLP) architectures, which extract complementary features, enhancing the model’s ability to capture pixel-level relationships and remove noise effectively. The final FB refines the processed image to generate a clean result. Experimental results demonstrate that CTCNet consistently outperforms several existing denoising techniques, achieving superior performance on both synthetic and real-world noise removal tasks.
Förderung
- University of Danang – University of Science and Technology
Zitieren
APA
Pham, C. T., & Phan, M. N. (2026). Multi-stage cross-transformer-based CNN for image denoising. The Computer Journal, 69(11), 1794-1815. https://doi.org/10.1093/comjnl/bxag059
Vancouver
Pham CT, Phan MN. Multi-stage cross-transformer-based CNN for image denoising. The Computer Journal. 2026;69(11):1794-1815. doi:10.1093/comjnl/bxag059
BibTeX
@article{Pham2026,
author = {Pham, Cong Thang and Phan, Minh Nhat},
title = {Multi-stage cross-transformer-based CNN for image denoising},
journal = {The Computer Journal},
year = {2026},
volume = {69},
number = {11},
pages = {1794--1815},
doi = {10.1093/comjnl/bxag059}
}
EUVIMED