EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Efficient Multi-Scale Attention Feature Fusion Network for 4K Video Frame Interpolation

Xin Ning, Yuhang Li, Ziwei Feng, Jinhua Liu, Youdong Ding

Electronics · 11.03.2024 · 13 (6) · 1037

DOI: 10.3390/electronics13061037 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 11.03.2024. Verfasst von Xin Ning und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shanghai Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Video frame interpolation aims to generate intermediate frames in a video to showcase finer details. However, most methods are only trained and tested on low-resolution datasets, lacking research on 4K video frame interpolation problems. This limitation makes it challenging to handle high-frame-rate video processing in real-world scenarios. In this paper, we propose a 4K video dataset at 120 fps, named UHD4K120FPS, which contains large motion. We also propose a novel framework for solving the 4K video frame interpolation task, based on a multi-scale pyramid network structure. We introduce self-attention to capture long-range dependencies and self-similarities in pixel space, which overcomes the limitations of convolutional operations. To reduce computational cost, we use a simple mapping-based approach to lighten self-attention, while still allowing for content-aware aggregation weights. Through extensive quantitative and qualitative experiments, we demonstrate the excellent performance achieved by our proposed model on the UHD4K120FPS dataset, as well as illustrate the effectiveness of our method for 4K video frame interpolation. In addition, we evaluate the robustness of the model on low-resolution benchmark datasets.

Förderung

  • National Natural Science Foundation of China
  • Shanghai Natural Science Foundation

Zitieren

APA

Ning, X., Li, Y., Feng, Z., Liu, J., & Ding, Y. (2024). An Efficient Multi-Scale Attention Feature Fusion Network for 4K Video Frame Interpolation. Electronics, 13(6), 1037. https://doi.org/10.3390/electronics13061037

Vancouver

Ning X, Li Y, Feng Z, Liu J, Ding Y. An Efficient Multi-Scale Attention Feature Fusion Network for 4K Video Frame Interpolation. Electronics. 2024;13(6):1037. doi:10.3390/electronics13061037

BibTeX
@article{Ning2024,
  author = {Ning, Xin and Li, Yuhang and Feng, Ziwei and Liu, Jinhua and Ding, Youdong},
  title = {An Efficient Multi-Scale Attention Feature Fusion Network for 4K Video Frame Interpolation},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {6},
  pages = {1037},
  doi = {10.3390/electronics13061037}
}
Kostenlos starten →