EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Frequency-Separated Attention Network for Image Super-Resolution

Daokuan Qu, Liulian Li, Rui Yao

Applied Sciences · 16.05.2024 · 14 (10) · 4238

DOI: 10.3390/app14104238 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 16.05.2024. Verfasst von Daokuan Qu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xuzhou Key Research and Development Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The use of deep convolutional neural networks has significantly improved the performance of super-resolution. Employing deeper networks to enhance the non-linear mapping capability from low-resolution (LR) to high-resolution (HR) images has inadvertently weakened the information flow and disrupted long-term memory. Moreover, overly deep networks are challenging to train, thus failing to exhibit the expressive capability commensurate with their depth. High-frequency and low-frequency features in images play different roles in image super-resolution. Networks based on CNNs, which should focus more on high-frequency features, treat these two types of features equally. This results in redundant computations when processing low-frequency features and causes complex and detailed parts of the reconstructed images to appear as smooth as the background. To maintain long-term memory and focus more on the restoration of image details in networks with strong representational capabilities, we propose the Frequency-Separated Attention Network (FSANet), where dense connections ensure the full utilization of multi-level features. In the Feature Extraction Module (FEM), the use of the Res ASPP Module expands the network’s receptive field without increasing its depth. To differentiate between high-frequency and low-frequency features within the network, we introduce the Feature-Separated Attention Block (FSAB). Furthermore, to enhance the quality of the restored images using heuristic features, we incorporate attention mechanisms into the Low-Frequency Attention Block (LFAB) and the High-Frequency Attention Block (HFAB) for processing low-frequency and high-frequency features, respectively. The proposed network outperforms the current state-of-the-art methods in tests on benchmark datasets.

Förderung

  • Xuzhou Key Research and Development Program

Zitieren

APA

Qu, D., Li, L., & Yao, R. (2024). Frequency-Separated Attention Network for Image Super-Resolution. Applied Sciences, 14(10), 4238. https://doi.org/10.3390/app14104238

Vancouver

Qu D, Li L, Yao R. Frequency-Separated Attention Network for Image Super-Resolution. Applied Sciences. 2024;14(10):4238. doi:10.3390/app14104238

BibTeX
@article{Qu2024,
  author = {Qu, Daokuan and Li, Liulian and Yao, Rui},
  title = {Frequency-Separated Attention Network for Image Super-Resolution},
  journal = {Applied Sciences},
  year = {2024},
  volume = {14},
  number = {10},
  pages = {4238},
  doi = {10.3390/app14104238}
}
Kostenlos starten →