MSEConv: A Unified Warping Framework for Video Frame Interpolation
ACM Transactions on Asian and Low-Resource Language Information Processing · 14.02.2024
DOI: 10.1145/3648364 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Asian and Low-Resource Language Information Processing, online erschienen am 14.02.2024. Verfasst von Xiangling Ding und 7 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 55 Literaturangaben.
Abstract (Originalsprache)
Within the context of video frame interpolation, complex motion modeling is the task of capturing, in a video sequence, where the moving objects are located in the interpolated frame, and how to maintain the temporal consistency of motion. Existing video frame interpolation methods typically assign either a fixed size of the motion kernel or a refined optical flow to model complex motions. However, they have the limitation of data redundancy and inaccuracy representation of motion. This paper introduces a unified warping framework, named multi-scale expandable deformable convolution (MSEConv), for simultaneously performing complex motion modeling and frame interpolation. In the proposed framework, a deep fully convolutional neural network with global attention is proposed to estimate multiple small-scale kernel weights with different expansion degrees and adaptive weight allocation for each pixel synthesis. Moreover, most of the kernel-based interpolation methods can be treated as the special case of the proposed MSEConv, thus, MSEConv can be easily transferred to other kernel-based frame interpolation methods for performance improvement. To further improve the robustness of motion occlusions, an operation of mask occlusion is introduced. As a consequence, our proposed MSEConv shows strong performance on par or even better than the state-of-the-art kernel-based frame interpolation works on public datasets. Our source code and visual comparable results are available at https://github.com/Pumpkin123709/MSEConv.
Zitieren
APA
Ding, X., Huang, P., Zhang, D., Liang, W., Li, F., Yang, G., Liao, X., & Li, Y. (2024). MSEConv: A Unified Warping Framework for Video Frame Interpolation. ACM Transactions on Asian and Low-Resource Language Information Processing. https://doi.org/10.1145/3648364
Vancouver
Ding X, Huang P, Zhang D, Liang W, Li F, Yang G, et al. MSEConv: A Unified Warping Framework for Video Frame Interpolation. ACM Transactions on Asian and Low-Resource Language Information Processing. 2024. doi:10.1145/3648364
BibTeX
@article{Ding2024,
author = {Ding, Xiangling and Huang, Pu and Zhang, Dengyong and Liang, Wei and Li, Feng and Yang, Gaobo and Liao, Xin and Li, Yue},
title = {MSEConv: A Unified Warping Framework for Video Frame Interpolation},
journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
year = {2024},
doi = {10.1145/3648364}
}
EUVIMED