EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Wavelet-Based, Blur-Aware Decoupled Network for Video Deblurring

Hua Wang, Pornntiwa Pawara, Rapeeporn Chamchong

Applied Sciences · 27.01.2025 · 15 (3) · 1311

DOI: 10.3390/app15031311 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 27.01.2025. Verfasst von Hua Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mahasarakham University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Video deblurring faces a fundamental challenge, as blur degradation comprehensively affects frames by not only causing detail loss but also severely distorting structural information. This dual degradation across low- and high-frequency domains makes it challenging for existing methods to simultaneously restore both structural and detailed information through a unified approach. To address this issue, we propose a wavelet-based, blur-aware decoupled network (WBDNet) that innovatively decouples structure reconstruction from detail enhancement. Our method decomposes features into multiple frequency bands and employs specialized restoration strategies for different frequency domains. In the low-frequency domain, we construct a multi-scale feature pyramid with optical flow alignment. This enables accurate structure reconstruction through bottom-up progressive feature fusion. For high-frequency components, we combine deformable convolution with a blur-aware attention mechanism. This allows us to precisely extract and merge sharp details from multiple frames. Extensive experiments on benchmark datasets demonstrate the superior performance of our method, particularly in preserving structural integrity and detail fidelity.

Förderung

  • Mahasarakham University

Zitieren

APA

Wang, H., Pawara, P., & Chamchong, R. (2025). Wavelet-Based, Blur-Aware Decoupled Network for Video Deblurring. Applied Sciences, 15(3), 1311. https://doi.org/10.3390/app15031311

Vancouver

Wang H, Pawara P, Chamchong R. Wavelet-Based, Blur-Aware Decoupled Network for Video Deblurring. Applied Sciences. 2025;15(3):1311. doi:10.3390/app15031311

BibTeX
@article{Wang2025,
  author = {Wang, Hua and Pawara, Pornntiwa and Chamchong, Rapeeporn},
  title = {Wavelet-Based, Blur-Aware Decoupled Network for Video Deblurring},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {3},
  pages = {1311},
  doi = {10.3390/app15031311}
}
Kostenlos starten →