EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ADE-CycleGAN: A Detail Enhanced Image Dehazing CycleGAN Network

Bingnan Yan, Zhaozhao Yang iD, Huizhu Sun, Conghui Wang

Sensors · 21.03.2023 · 23 (6) · 3294

DOI: 10.3390/s23063294 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.03.2023. Verfasst von Bingnan Yan und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Engineering, Xi'an Shiyou University, Xi'an 710065, China. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Postgraduate Innovation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The preservation of image details in the defogging process is still one key challenge in the field of deep learning. The network uses the generation of confrontation loss and cyclic consistency loss to ensure that the generated defog image is similar to the original image, but it cannot retain the details of the image. To this end, we propose a detail enhanced image CycleGAN to retain the detail information during the process of defogging. Firstly, the algorithm uses the CycleGAN network as the basic framework and combines the U-Net network’s idea with this framework to extract visual information features in different spaces of the image in multiple parallel branches, and it introduces Dep residual blocks to learn deeper feature information. Secondly, a multi-head attention mechanism is introduced in the generator to strengthen the expressive ability of features and balance the deviation produced by the same attention mechanism. Finally, experiments are carried out on the public data set D-Hazy. Compared with the CycleGAN network, the network structure of this paper improves the SSIM and PSNR of the image dehazing effect by 12.2% and 8.1% compared with the network and can retain image dehazing details.

Schlagwörter

Stichwörter der Autor:innen

CycleGANDep residual blocksimage defoggingmulti-head attention

Autor:innen und Institutionen

  • School of Electronic Engineering, Xi'an Shiyou University, Xi'an 710065, China.

ORCID-Profile: Zhaozhao Yang

Förderung

  • National Natural Science Foundation of China
  • Postgraduate Innovation

Zitieren

APA

Yan, B., Yang, Z., Sun, H., & Wang, C. (2023). ADE-CycleGAN: A Detail Enhanced Image Dehazing CycleGAN Network. Sensors, 23(6), 3294. https://doi.org/10.3390/s23063294

Vancouver

Yan B, Yang Z, Sun H, Wang C. ADE-CycleGAN: A Detail Enhanced Image Dehazing CycleGAN Network. Sensors. 2023;23(6):3294. doi:10.3390/s23063294

BibTeX
@article{Yan2023,
  author = {Yan, Bingnan and Yang, Zhaozhao and Sun, Huizhu and Wang, Conghui},
  title = {ADE-CycleGAN: A Detail Enhanced Image Dehazing CycleGAN Network},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {6},
  pages = {3294},
  doi = {10.3390/s23063294}
}
Kostenlos starten →