Channel Attention Is All You Need for Video Frame Interpolation


  • Myungsub Choi Seoul National University
  • Heewon Kim Seoul National University
  • Bohyung Han Seoul National University
  • Ning Xu Amazon Go
  • Kyoung Mu Lee Seoul National University



Prevailing video frame interpolation techniques rely heavily on optical flow estimation and require additional model complexity and computational cost; it is also susceptible to error propagation in challenging scenarios with large motion and heavy occlusion. To alleviate the limitation, we propose a simple but effective deep neural network for video frame interpolation, which is end-to-end trainable and is free from a motion estimation network component. Our algorithm employs a special feature reshaping operation, referred to as PixelShuffle, with a channel attention, which replaces the optical flow computation module. The main idea behind the design is to distribute the information in a feature map into multiple channels and extract motion information by attending the channels for pixel-level frame synthesis. The model given by this principle turns out to be effective in the presence of challenging motion and occlusion. We construct a comprehensive evaluation benchmark and demonstrate that the proposed approach achieves outstanding performance compared to the existing models with a component for optical flow computation.




How to Cite

Choi, M., Kim, H., Han, B., Xu, N., & Lee, K. M. (2020). Channel Attention Is All You Need for Video Frame Interpolation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 10663-10671.



AAAI Technical Track: Vision