EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

MWA-Net: multi-scale wavelet-guided attention network for single image dehazing

Yijian Wu, Zewen Chen, Weichao Yi, Yulin Yang

Complex & Intelligent Systems · 2025-10 · 11 (10)

DOI: 10.1007/s40747-025-02076-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Complex & Intelligent Systems, online erschienen am 11.09.2025. Verfasst von Yijian Wu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The growing interest in image haze removal has driven significant advancements in deep learning-based algorithms, exhibiting promising performance in recent studies. However, due to the uneven and complex distribution of haze in real-world scenarios, existing single-scale models are constrained by their restricted receptive fields, making it challenging to effectively address intricate hazy environments. Besides, conventional down-sampling operations may easily suffer from loss of details and color distortion when reducing the feature resolution, hindering the realization of better haze removal performance. To this end, we propose a Multi-scale Wavelet-guided Attention Network (MWA-Net) for haze removal. For one thing, our MWA-Net relies on an efficient multi-stage architecture that progressively enlarges receptive fields from multi-scale degraded hazy inputs, effectively capturing global content information for better haze removal in complex scenarios. Meanwhile, we incorporate a novel mixed attention mechanism that includes Channel Attention, Pixel Attention, and Supplementary Attention to further boost the feature learning for alleviating uneven haze distribution. For another, we leverage wavelet decomposition to extract low-frequency and high-frequency components from the feature layer for feature down-sampling and up-sampling, which enables the model to minimize texture detail loss and ensure high-quality feature reconstruction. Furthermore, an Attentive Fusion Scheme is designed to effectively integrate multi-scale features while overcoming the semantic and scale inconsistency issues among diverse inputs. Extensive experiments prove that our method MWA-Net can outperform against other compared state-of-the-art methods on several benchmarks.

Zitieren

APA

Wu, Y., Chen, Z., Yi, W., & Yang, Y. (2025). MWA-Net: multi-scale wavelet-guided attention network for single image dehazing. Complex & Intelligent Systems, 11(10). https://doi.org/10.1007/s40747-025-02076-4

Vancouver

Wu Y, Chen Z, Yi W, Yang Y. MWA-Net: multi-scale wavelet-guided attention network for single image dehazing. Complex & Intelligent Systems. 2025;11(10). doi:10.1007/s40747-025-02076-4

BibTeX
@article{Wu2025,
  author = {Wu, Yijian and Chen, Zewen and Yi, Weichao and Yang, Yulin},
  title = {MWA-Net: multi-scale wavelet-guided attention network for single image dehazing},
  journal = {Complex & Intelligent Systems},
  year = {2025},
  volume = {11},
  number = {10},
  doi = {10.1007/s40747-025-02076-4}
}
Kostenlos starten →