Kernel-Based Video Frame Interpolation Techniques Using Feature Map Differencing


KIPS Transactions on Software and Data Engineering, Vol. 13, No. 1, pp. 17-27, Jan. 2024
https://doi.org/10.3745/KTSDE.2024.13.1.17,   PDF Download:
Keywords: Deep Learning, Frame Differencing, Video Frame Interpolation, U-net
Abstract

Video frame interpolation is an important technique used in the field of video and media, as it increases the continuity of motion and enables smooth playback of videos. In the study of video frame interpolation using deep learning, Kernel Based Method captures local changes well, but has limitations in handling global changes. In this paper, we propose a new U-Net structure that applies feature map differentiation and two directions to focus on capturing major changes to generate intermediate frames more accurately while reducing the number of parameters. Experimental results show that the proposed structure outperforms the existing model by up to 0.3 in PSNR with about 61% fewer parameters on common datasets such as Vimeo, Middle-burry, and a new YouTube dataset. Code is available at https://github.com/Go-MinSeong/SF-AdaCoF.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
D. Seo, M. Ko, S. Lee, J. Park, "Kernel-Based Video Frame Interpolation Techniques Using Feature Map Differencing," KIPS Transactions on Software and Data Engineering, vol. 13, no. 1, pp. 17-27, 2024. DOI: https://doi.org/10.3745/KTSDE.2024.13.1.17.

[ACM Style]
Dong-Hyeok Seo, Min-Seong Ko, Seung-Hak Lee, and Jong-Hyuk Park. 2024. Kernel-Based Video Frame Interpolation Techniques Using Feature Map Differencing. KIPS Transactions on Software and Data Engineering, 13, 1, (2024), 17-27. DOI: https://doi.org/10.3745/KTSDE.2024.13.1.17.