EUVIMEDEUVIMED entdecken
Crossref

DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention

Zixuan Chen, Zewei He, Zhe-Ming Lu

IEEE Transactions on Image Processing · 2024 · 33 · 1002-1015

DOI: 10.1109/tip.2024.3354108 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Zixuan Chen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 986-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Zhejiang Provincial Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single image dehazing is a challenging ill-posed problem which estimates latent haze-free images from observed hazy images. Some existing deep learning based methods are devoted to improving the model performance via increasing the depth or width of convolution. The learning ability of Convolutional Neural Network (CNN) structure is still under-explored. In this paper, a Detail-Enhanced Attention Block (DEAB) consisting of Detail-Enhanced Convolution (DEConv) and Content-Guided Attention (CGA) is proposed to boost the feature learning for improving the dehazing performance. Specifically, the DEConv contains difference convolutions which can integrate prior information to complement the vanilla one and enhance the representation capacity. Then by using the re-parameterization technique, DEConv is equivalently converted into a vanilla convolution to reduce parameters and computational cost. By assigning the unique Spatial Importance Map (SIM) to every channel, CGA can attend more useful information encoded in features. In addition, a CGA-based mixup fusion scheme is presented to effectively fuse the features and aid the gradient flow. By combining above mentioned components, we propose our Detail-Enhanced Attention Network (DEA-Net) for recovering high-quality haze-free images. Extensive experimental results demonstrate the effectiveness of our DEA-Net, outperforming the state-of-the-art (SOTA) methods by boosting the PSNR index over 41 dB with only 3.653 M parameters. (The source code of our DEA-Net is available at https://github.com/cecret3350/DEA-Net.).

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Zhejiang Provincial Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • Hangzhou Major Scientific and Technological Innovation Projects

Zitieren

APA

Chen, Z., He, Z., & Lu, Z. M. (2024). DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention. IEEE Transactions on Image Processing, 33, 1002-1015. https://doi.org/10.1109/tip.2024.3354108

Vancouver

Chen Z, He Z, Lu ZM. DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention. IEEE Transactions on Image Processing. 2024;33:1002-1015. doi:10.1109/tip.2024.3354108

BibTeX
@article{Chen2024,
  author = {Chen, Zixuan and He, Zewei and Lu, Zhe-Ming},
  title = {DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention},
  journal = {IEEE Transactions on Image Processing},
  year = {2024},
  volume = {33},
  pages = {1002--1015},
  doi = {10.1109/tip.2024.3354108}
}
Kostenlos starten →