EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deformable Attention Multiscale Feature Fusion Network‐Dehaze: An Adaptive Image Dehazing Method Based on Deformable Attention Multiscale Fusion Network

Ruipeng Wang, Yajun Chen, Hao Liu, Mingrui Li, Zhiqi Li

Advanced Intelligent Systems · 2026-05 · 8 (5)

DOI: 10.1002/aisy.202501476 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Intelligent Systems, online erschienen am 15.03.2026. Verfasst von Ruipeng Wang und 4 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image dehazing, a fundamental computer vision task, is crucial for the stability of multiple downstream systems. Traditional methods have limited generalization, while deep learning methods face bottlenecks like error accumulation and poor adaptability. To address these, this paper proposes deformable attention multiscale feature fusion network‐dehaze, a deformable attention‐based multiscale feature fusion network with three core modules: the revised residual shrinkage unit uses deformable convolution to dynamically adjust receptive fields via real‐time fog density learning for precise adaptation to irregular fog regions; the hierarchical multiscale attention integrates channel and spatial attention to screen key features and restore fog‐obscured details; and the cross‐scale feature fusion adopts bidirectional transmission to fuse high‐level semantic and low‐level spatial features, compensating for downsampling‐induced spatial loss. Experiments on RESIDE and D‐HAZE show the method outperforms mainstream approaches, with peak signal‐to‐noise ratio improved by over 20% and SSIM by over 10% in some real fog scenes, verifying its superior accuracy and generalization.

Zitieren

APA

Wang, R., Chen, Y., Liu, H., Li, M., & Li, Z. (2026). Deformable Attention Multiscale Feature Fusion Network‐Dehaze: An Adaptive Image Dehazing Method Based on Deformable Attention Multiscale Fusion Network. Advanced Intelligent Systems, 8(5). https://doi.org/10.1002/aisy.202501476

Vancouver

Wang R, Chen Y, Liu H, Li M, Li Z. Deformable Attention Multiscale Feature Fusion Network‐Dehaze: An Adaptive Image Dehazing Method Based on Deformable Attention Multiscale Fusion Network. Advanced Intelligent Systems. 2026;8(5). doi:10.1002/aisy.202501476

BibTeX
@article{Wang2026,
  author = {Wang, Ruipeng and Chen, Yajun and Liu, Hao and Li, Mingrui and Li, Zhiqi},
  title = {Deformable Attention Multiscale Feature Fusion Network‐Dehaze: An Adaptive Image Dehazing Method Based on Deformable Attention Multiscale Fusion Network},
  journal = {Advanced Intelligent Systems},
  year = {2026},
  volume = {8},
  number = {5},
  doi = {10.1002/aisy.202501476}
}
Kostenlos starten →