EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Efficient Image Deblurring Network with a Hybrid Architecture

Mingju Chen, Sihang Yi, Zhongxiao Lan iD, Zhengxu Duan

Sensors · 18.08.2023 · 23 (16) · 7260

DOI: 10.3390/s23167260 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.08.2023. Verfasst von Mingju Chen und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644002, China. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Sichuan, The Key Laboratory of Internet Information Retrieval of Hainan Province Research Found, The Opening Project of International Joint Research Center for Robotics and Intelligence System of Sichuan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Blurring is one of the main degradation factors in image degradation, so image deblurring is of great interest as a fundamental problem in low-level computer vision. Because of the limited receptive field, traditional CNNs lack global fuzzy region modeling, and do not make full use of rich context information between features. Recently, a transformer-based neural network structure has performed well in natural language tasks, inspiring rapid development in the field of defuzzification. Therefore, in this paper, a hybrid architecture based on CNN and transformers is used for image deblurring. Specifically, we first extract the shallow features of the blurred images using a cross-layer feature fusion block that emphasizes the contextual information of each feature extraction layer. Secondly, an efficient transformer module for extracting deep features is designed, which fully aggregates feature information at medium and long distances using vertical and horizontal intra- and inter-strip attention layers, and a dual gating mechanism is used as a feedforward neural network, which effectively reduces redundant features. Finally, the cross-layer feature fusion block is used to complement the feature information to obtain the deblurred image. Extensive experimental results on publicly available benchmark datasets GoPro, HIDE, and the real dataset RealBlur show that the proposed method outperforms the current mainstream deblurring algorithms and recovers the edge contours and texture details of the images more clearly.

Schlagwörter

Stichwörter der Autor:innen

cross-layer feature fusionhybrid architectureimage deblurringtransformer

Autor:innen und Institutionen

  • School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644002, China.
  • Artificial Intelligence Key Laboratory of Sichuan Province, Sichuan University of Science & Engineering, Yibin 644002, China.

ORCID-Profile: Zhongxiao Lan

Förderung

  • Natural Science Foundation of Sichuan
  • The Key Laboratory of Internet Information Retrieval of Hainan Province Research Found
  • The Opening Project of International Joint Research Center for Robotics and Intelligence System of Sichuan Province
  • Sichuan University of Science and Engineering Postgraduate Innovation Fund in 2022
  • Key Laboratory of Internet Information Retrieval of Hainan Province Research Fund

Zitieren

APA

Chen, M., Yi, S., Lan, Z., & Duan, Z. (2023). An Efficient Image Deblurring Network with a Hybrid Architecture. Sensors, 23(16), 7260. https://doi.org/10.3390/s23167260

Vancouver

Chen M, Yi S, Lan Z, Duan Z. An Efficient Image Deblurring Network with a Hybrid Architecture. Sensors. 2023;23(16):7260. doi:10.3390/s23167260

BibTeX
@article{Chen2023,
  author = {Chen, Mingju and Yi, Sihang and Lan, Zhongxiao and Duan, Zhengxu},
  title = {An Efficient Image Deblurring Network with a Hybrid Architecture},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {16},
  pages = {7260},
  doi = {10.3390/s23167260}
}
Kostenlos starten →