Corpus ID: 229181044

FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation

@article{Kalluri2020FLAVRFV,
  title={FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation},
  author={Tarun Kalluri and Deepak Pathak and Manmohan Chandraker and Du Tran},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.08512}
}
A majority of approaches solve the problem of video frame interpolation by computing bidirectional optical flow between adjacent frames of a video followed by a suitable warping algorithm to generate the output frames. However, methods relying on optical flow often fail to model occlusions and complex non-linear motions directly from the video and introduce additional bottlenecks unsuitable for real time deployment. To overcome these limitations, we propose a flexible and efficient architecture… Expand
Efficient Space-time Video Super Resolution using Low-Resolution Flow and Mask Upsampling
NTIRE 2021 Challenge on Video Super-Resolution

References

SHOWING 1-10 OF 79 REFERENCES
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
Depth-Aware Video Frame Interpolation
Channel Attention Is All You Need for Video Frame Interpolation
AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation
PhaseNet for Video Frame Interpolation
Video Frame Synthesis Using Deep Voxel Flow
Context-Aware Synthesis for Video Frame Interpolation
  • Simon Niklaus, Feng Liu
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
Scene-Adaptive Video Frame Interpolation via Meta-Learning
Video Frame Interpolation via Deformable Separable Convolution
Deep Video Frame Interpolation Using Cyclic Frame Generation
...
1
2
3
4
5
...