Corpus ID: 212675709

Softmax Splatting for Video Frame Interpolation

@article{Niklaus2020SoftmaxSF,
  title={Softmax Splatting for Video Frame Interpolation},
  author={Simon Niklaus and Feng Liu},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.05534}
}
  • Simon Niklaus, Feng Liu
  • Published in ArXiv 2020
  • Computer Science
  • Differentiable image sampling in the form of backward warping has seen broad adoption in tasks like depth estimation and optical flow prediction. In contrast, how to perform forward warping has seen less attention, partly due to additional challenges such as resolving the conflict of mapping multiple pixels to the same target location in a differentiable way. We propose softmax splatting to address this paradigm shift and show its effectiveness on the application of frame interpolation… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 63 REFERENCES

    Depth-Aware Video Frame Interpolation

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL

    Context-Aware Synthesis for Video Frame Interpolation

    • Simon Niklaus, Feng Liu
    • Computer Science
    • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
    • 2018
    VIEW 10 EXCERPTS

    PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    A Database and Evaluation Methodology for Optical Flow

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Lite- FlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation

    • Tak-Wai Hui, Xiaoou Tang, Chen Change Loy
    • In IEEE Conference on Computer Vision and Pattern Recognition,
    • 2018
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Video Frame Synthesis Using Deep Voxel Flow

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Spatial Transformer Networks

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL