EUVIMEDEUVIMED entdecken
Crossref

Implicit Multi-Scale Swin Transformer Network for Image Denoising

Qi Zhang, Yuwei Ding, Weiqi Zhang, Yian Zhu, Bob Zhang, Jerry Chun-Wei Lin

IEEE Transactions on Consumer Electronics · 2025-05 · 71 (2) · 5584-5594

DOI: 10.1109/tce.2025.3565390 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-05. Verfasst von Qi Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: State Key Laboratory for Novel Software Technology, Nanjing University, Shaanxi Province Science Foundation for Youths, Leading Talents in Gusu Innovation and Entrepreneurship.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image denoising has been used in various edge computing scenarios such as consumer electronics to improve the image quality and user experience. Existing image denoising methods based on Convolutional Neural Networks (CNNs) and vision Transformers achieve good performance by empirically utilizing residual neural network (ResNet) as basic component. However, ResNet lacks interpretability in network design and also long-term memory of features, potentially restricting the performance of denoising networks. In this paper, we propose an Implicit Multi-scale Swin Transformer Network (IMSNet) for image denoising, which introduces the implicit Euler scheme from the feature memory perspective. Specifically, densely connected implicit feature extraction blocks (IFEBs) are designed to learn the residual mapping between noisy and clean images. The IFEB reformulates the initial skip connection of ResNet based on the implicit Euler discretization, providing both network interpretability and long-term memory. In IFEB, the multi-scale swin Transformer block (MSB) is designed as the implicit layer to capture spatial details and non-local contextual information at different scales. Additionally, a cross-layer feature fusion block (CLFF) is proposed to further improve feature reuse capabilities. Compared to existing denoising networks, the extensive experiments demonstrate the superior performance of our IMSNet in various image denoising tasks, and the flexibility in the practical applications with proposed light model on resource-restricted platforms such as consumer electronic devices.

Förderung

  • State Key Laboratory for Novel Software Technology, Nanjing University
  • Shaanxi Province Science Foundation for Youths
  • Leading Talents in Gusu Innovation and Entrepreneurship
  • Basic Research Plan in Taicang
  • Universidade de Macau

Zitieren

APA

Zhang, Q., Ding, Y., Zhang, W., Zhu, Y., Zhang, B., & Lin, J. C. (2025). Implicit Multi-Scale Swin Transformer Network for Image Denoising. IEEE Transactions on Consumer Electronics, 71(2), 5584-5594. https://doi.org/10.1109/tce.2025.3565390

Vancouver

Zhang Q, Ding Y, Zhang W, Zhu Y, Zhang B, Lin JC. Implicit Multi-Scale Swin Transformer Network for Image Denoising. IEEE Transactions on Consumer Electronics. 2025;71(2):5584-5594. doi:10.1109/tce.2025.3565390

BibTeX
@article{Zhang2025,
  author = {Zhang, Qi and Ding, Yuwei and Zhang, Weiqi and Zhu, Yian and Zhang, Bob and Lin, Jerry Chun-Wei},
  title = {Implicit Multi-Scale Swin Transformer Network for Image Denoising},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2025},
  volume = {71},
  number = {2},
  pages = {5584--5594},
  doi = {10.1109/tce.2025.3565390}
}
Kostenlos starten →