EUVIMEDEUVIMED entdecken
Crossref

Locally Adaptive Channel Attention-Based Spatial–Spectral Neural Network for Image Deblurring

Ho Sub Lee, Sung In Cho

IEEE Transactions on Circuits and Systems for Video Technology · 2023-10 · 33 (10) · 5375-5390

DOI: 10.1109/tcsvt.2023.3250509 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-10. Verfasst von Ho Sub Lee und 1 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: National Research Foundation of Korea, Korea Government.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, due to the rapid development of deep neural networks in the field of computer vision, many studies have been conducted in the field of image deblurring. However, previous methods cannot attain satisfactory deblurring performance in object boundaries and local regions containing image details in restored results. This paper proposes a new method that uses a locally adaptive channel attention module for a spectral–spatial network to resolve the problem of single-image deblurring. Unlike existing methods, our proposed method consists of a spectral restorer and spatial restorer that adopt a locally adaptive attention mechanism in the spectral–spatial domains. In addition, unlike a conventional spectral–spatial network that only considers the magnitude of the frequency coefficients, the proposed method uses both the magnitude and phase of the frequency coefficients in the training stage. Our locally adaptive channel attention spectral–spatial network can focus on informative channels that are closely related to blur artifacts. Specifically, the spatial restorer, which guides the intensity of the blur image to fit the ground truth by exploring the interdependencies of feature channels, can efficiently restore scene characteristics while the spectral restorer, which guides the magnitude and phase of the blur image’s frequency coefficients to fit those of the ground truth by exploring the interdependencies of feature channels, fine-tunes the details of structures. The experimental results show that the proposed method outperformed the deblurring results compared to benchmark methods in terms of both qualitative evaluation and quantitative metrics.

Förderung

  • National Research Foundation of Korea
  • Korea Government

Zitieren

APA

Lee, H. S., & Cho, S. I. (2023). Locally Adaptive Channel Attention-Based Spatial–Spectral Neural Network for Image Deblurring. IEEE Transactions on Circuits and Systems for Video Technology, 33(10), 5375-5390. https://doi.org/10.1109/tcsvt.2023.3250509

Vancouver

Lee HS, Cho SI. Locally Adaptive Channel Attention-Based Spatial–Spectral Neural Network for Image Deblurring. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(10):5375-5390. doi:10.1109/tcsvt.2023.3250509

BibTeX
@article{Lee2023,
  author = {Lee, Ho Sub and Cho, Sung In},
  title = {Locally Adaptive Channel Attention-Based Spatial–Spectral Neural Network for Image Deblurring},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {10},
  pages = {5375--5390},
  doi = {10.1109/tcsvt.2023.3250509}
}
Kostenlos starten →