EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-World Video Super-Resolution with a Degradation-Adaptive Model

Mingxuan Lu iD, Peng Zhang iD

Sensors · 29.03.2024 · 24 (7) · 2211

DOI: 10.3390/s24072211 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.03.2024. Verfasst von Mingxuan Lu und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-Sen University, Shenzhen 518107, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shenzhen Science and Technology Program, the Science and Technology Planning Project of Guangdong Science and Technology Department under Grant Guangdong Key Laboratory of Advanced IntelliSense Techno…, the Science and Technology Planning Project of Guangdong Science and Technology Department.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Video super-resolution (VSR) remains challenging for real-world applications due to complex and unknown degradations. Existing methods lack the flexibility to handle video sequences with different degradation levels, thus failing to reflect real-world scenarios. To address this problem, we propose a degradation-adaptive video super-resolution network (DAVSR) based on a bidirectional propagation network. Specifically, we adaptively employ three distinct degradation levels to process input video sequences, aiming to obtain training pairs that reflect a variety of real-world corrupted images. We also equip the network with a pre-cleaning module to reduce noise and artifacts in the low-quality video sequences prior to information propagation. Additionally, compared to previous flow-based methods, we employ an unsupervised optical flow estimator to acquire a more precise optical flow to guide inter-frame alignment. Meanwhile, while maintaining network performance, we streamline the propagation network branches and the structure of the reconstruction module of the baseline network. Experiments are conducted on datasets with diverse degradation types to validate the effectiveness of DAVSR. Our method exhibits an average improvement of 0.18 dB over a recent SOTA approach (DBVSR) in terms of the PSNR metric. Extensive experiments demonstrate the effectiveness of our network in handling real-world video sequences with different degradation levels.

Schlagwörter

Stichwörter der Autor:innen

deep learningdegradation-adaptivelightweight networkpre-cleaningreal-world video super-resolution

Autor:innen und Institutionen

  • School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-Sen University, Shenzhen 518107, China.

ORCID-Profile: Mingxuan Lu, Peng Zhang

Förderung

  • Shenzhen Science and Technology Program
  • the Science and Technology Planning Project of Guangdong Science and Technology Department under Grant Guangdong Key Laboratory of Advanced IntelliSense Techno…
  • the Science and Technology Planning Project of Guangdong Science and Technology Department

Zitieren

APA

Lu, M., & Zhang, P. (2024). Real-World Video Super-Resolution with a Degradation-Adaptive Model. Sensors, 24(7), 2211. https://doi.org/10.3390/s24072211

Vancouver

Lu M, Zhang P. Real-World Video Super-Resolution with a Degradation-Adaptive Model. Sensors. 2024;24(7):2211. doi:10.3390/s24072211

BibTeX
@article{Lu2024,
  author = {Lu, Mingxuan and Zhang, Peng},
  title = {Real-World Video Super-Resolution with a Degradation-Adaptive Model},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {7},
  pages = {2211},
  doi = {10.3390/s24072211}
}
Kostenlos starten →