EUVIMEDEUVIMED entdecken
Crossref

A Lightweight U-Shaped Transformer Network for Single Image Dehazing

Yiping Zhang, Youbo Lian

Information Technology and Control · 25.09.2026 · 55 (3) · 1406-1423

DOI: 10.5755/j01.itc.55.3.45302 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information Technology and Control, online erschienen am 25.09.2026. Verfasst von Yiping Zhang und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single-image dehazing aims to restore a clear image from a single haze-degraded observation. Although recent deep learning methods have shown promising performance, they still struggle to balance long-range dependency modelling and computational efficiency. To address this issue, we propose a lightweight U-shaped Transformer network, termed UTNet. The proposed network adopts a U-shaped encoder-decoder architecture to progressively extract and reconstruct hierarchical features, enabling effective integration of shallow spatial details and deep contextual information. To reduce the computational burden of Transformer-based modelling, local-window spatial attention is introduced at each stage to efficiently model dependencies. Unlike Swin Transformer, UTNet leverages its hierarchical U-shaped architecture to enlarge the receptive field and progressively capture global contextual information. In addition, channel attention is incorporated in parallel with spatial attention to enhance feature representation further. Multi-scale auxiliary supervision is also introduced to improve optimization stability and promote consistent restoration from coarse structures to fine details. Moreover, gamma-based data augmentation is employed to improve the model generalization to real-world hazy images. Extensive experiments on the Haze4K and NH-Haze datasets demonstrate that the proposed UTNet achieves competitive dehazing performance while maintaining a compact architecture with fewer parameters and lower computational cost.

Zitieren

APA

Zhang, Y., & Lian, Y. (2026). A Lightweight U-Shaped Transformer Network for Single Image Dehazing. Information Technology and Control, 55(3), 1406-1423. https://doi.org/10.5755/j01.itc.55.3.45302

Vancouver

Zhang Y, Lian Y. A Lightweight U-Shaped Transformer Network for Single Image Dehazing. Information Technology and Control. 2026;55(3):1406-1423. doi:10.5755/j01.itc.55.3.45302

BibTeX
@article{Zhang2026,
  author = {Zhang, Yiping and Lian, Youbo},
  title = {A Lightweight U-Shaped Transformer Network for Single Image Dehazing},
  journal = {Information Technology and Control},
  year = {2026},
  volume = {55},
  number = {3},
  pages = {1406--1423},
  doi = {10.5755/j01.itc.55.3.45302}
}
Kostenlos starten →