EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention

Yanfei Chen, Tong Yue, Pei An, Hanyu Hong, Tao Liu, Yangkai Liu, Yihui Zhou

Sensors · 15.06.2025 · 25 (12) · 3750

DOI: 10.3390/s25123750 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.06.2025. Verfasst von Yanfei Chen und 6 weiteren Autor:innen. Beteiligte Einrichtung: Hubei Key Laboratory of Optical Information and Pattern Recognition, School of Electrical and Information Engineering, Wuhan Institute of Technology,…. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The National Natural Science Foundation of China, The Graduate Innovative Fund of Wuhan Institute of Technology, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single image dehazing is a fundamental task in computer vision, aiming to recover a clear scene from a hazy input image. To address the limitations of traditional dehazing algorithms—particularly in global feature association and local detail preservation—this study proposes a novel Transformer-based dehazing model enhanced by an interactive channel attention mechanism. The proposed architecture adopts a U-shaped encoder–decoder framework, incorporating key components such as a feature extraction module and a feature fusion module based on interactive attention. Specifically, the interactive channel attention mechanism facilitates cross-layer feature interaction, enabling the dynamic fusion of global contextual information and local texture details. The network architecture leverages a multi-scale feature pyramid to extract image information across different dimensions, while an improved cross-channel attention weighting mechanism enhances feature representation in regions with varying haze densities. Extensive experiments conducted on both synthetic and real-world datasets—including the RESIDE benchmark—demonstrate the superior performance of the proposed method. Quantitatively, it achieves PSNR gains of 0.53 dB for indoor scenes and 1.64 dB for outdoor scenes, alongside SSIM improvements of 1.4% and 1.7%, respectively, compared with the second-best performing method. Qualitative assessments further confirm that the proposed model excels in restoring fine structural details in dense haze regions while maintaining high color fidelity. These results validate the effectiveness of the proposed approach in enhancing both perceptual quality and quantitative accuracy in image dehazing tasks.

Schlagwörter

Stichwörter der Autor:innen

Transformerattention mechanismfeature extractionimage dehaze

Autor:innen und Institutionen

  • Hubei Key Laboratory of Optical Information and Pattern Recognition, School of Electrical and Information Engineering, Wuhan Institute of Technology, Wuhan 430205, China.
  • School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430072, China.

Förderung

  • The National Natural Science Foundation of China
  • The Graduate Innovative Fund of Wuhan Institute of Technology
  • National Natural Science Foundation of China
  • Graduate Innovative Fund of Wuhan Institute of Technology

Zitieren

APA

Chen, Y., Yue, T., An, P., Hong, H., Liu, T., Liu, Y., & Zhou, Y. (2025). ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention. Sensors, 25(12), 3750. https://doi.org/10.3390/s25123750

Vancouver

Chen Y, Yue T, An P, Hong H, Liu T, Liu Y, et al. ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention. Sensors. 2025;25(12):3750. doi:10.3390/s25123750

BibTeX
@article{Chen2025,
  author = {Chen, Yanfei and Yue, Tong and An, Pei and Hong, Hanyu and Liu, Tao and Liu, Yangkai and Zhou, Yihui},
  title = {ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {12},
  pages = {3750},
  doi = {10.3390/s25123750}
}
Kostenlos starten →