RABNet: A Residual Attention‐Based Network for Visibility Restoration in Hazy Images
IET Computers & Digital Techniques · 2026-01 · 2026 (1)
DOI: 10.1049/cdt2/8366822 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Computers & Digital Techniques, online erschienen am 09.06.2026. Verfasst von Syeda Rabail Zahra und 7 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Princess Nourah Bint Abdulrahman University.
Abstract (Originalsprache)
Image dehazing enhances visibility and image quality, enabling better decision‐making in critical applications such as surveillance, remote sensing, and autonomous driving. However, single‐image dehazing remains challenging due to the need for smoothness in homogeneous regions, accurate edge preservation, texture fidelity, and artifact‐free reconstruction. In this paper, we propose RABNet, a novel deep learning framework for single‐image dehazing. Traditional approaches often suffer from lossy reconstruction and poor performance under uneven haze distribution. RABNet addresses these limitations by integrating three key modules: the Hazy Feature Extraction Module (HFEM), Visibility Restoration Module (VRM), and Dehazed Image Reconstruction Module (DIRM). The HFEM enhances the network’s ability to perceive haze characteristics across varying lighting, contrast, and structural scales, providing a strong foundation for restoration. The VRM promotes feature diversity by employing multiple activation functions and an attention mechanism to refine visibility cues. Finally, the DIRM reconstructs the clean image by estimating the residual haze component and combining it with the input. By modeling haze‐related features effectively, RABNet restores the underlying clean image while preserving color, texture, and structural details. Extensive experiments on both synthetic and real‐world datasets, including FRIDA, O‐HAZE, I‐HAZE, and NH‐HAZE, demonstrate the robustness and superior performance of RABNet, achieving state‐of‐the‐art results in terms of PSNR and SSIM.
Förderung
- Princess Nourah Bint Abdulrahman University
Zitieren
APA
Zahra, S. R., Hussain, F., Hassan, A., Mazhar, T., Al-Rasheed, A., Khan, M. A., Ahmad, W., & Hamam, H. (2026). RABNet: A Residual Attention‐Based Network for Visibility Restoration in Hazy Images. IET Computers & Digital Techniques, 2026(1). https://doi.org/10.1049/cdt2/8366822
Vancouver
Zahra SR, Hussain F, Hassan A, Mazhar T, Al-Rasheed A, Khan MA, et al. RABNet: A Residual Attention‐Based Network for Visibility Restoration in Hazy Images. IET Computers & Digital Techniques. 2026;2026(1). doi:10.1049/cdt2/8366822
BibTeX
@article{Zahra2026,
author = {Zahra, Syeda Rabail and Hussain, Farhan and Hassan, Ali and Mazhar, Tehseen and Al-Rasheed, Amal and Khan, Muhammad Amir and Ahmad, Wasim and Hamam, Habib},
title = {RABNet: A Residual Attention‐Based Network for Visibility Restoration in Hazy Images},
journal = {IET Computers & Digital Techniques},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1049/cdt2/8366822}
}
EUVIMED