A survey of variational and CNN-based optical flow techniques

@article{Tu2019ASO,
  title={A survey of variational and CNN-based optical flow techniques},
  author={Zhigang Tu and Wei Xie and Dejun Zhang and Ronald Poppe and Remco C. Veltkamp and Baoxin Li and Junsong Yuan},
  journal={Signal Process. Image Commun.},
  year={2019},
  volume={72},
  pages={9-24}
}
  • Zhigang Tu, Wei Xie, +4 authors Junsong Yuan
  • Published in Signal Process. Image Commun. 2019
  • Computer Science
  • Abstract Dense motion estimations obtained from optical flow techniques play a significant role in many image processing and computer vision tasks. Remarkable progress has been made in both theory and its application in practice. In this paper, we provide a systematic review of recent optical flow techniques with a focus on the variational method and approaches based on Convolutional Neural Networks (CNNs). These two categories have led to state-of-the-art performance. We discuss recent… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 217 REFERENCES

    A Database and Evaluation Methodology for Optical Flow

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Variational Optic Flow Computation: Accurate Modelling and Efficient Numerics (Ph.D

    • A. Bruhn
    • 2006
    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Highly Accurate Optic Flow Computation with Theoretically Justified Warping

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Determining Optical Flow

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Optic Flow in Harmony

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Sparse Occlusion Detection with Optical Flow

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Motion Detail Preserving Optical Flow Estimation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Secrets of optical flow estimation and their principles

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    An Improved Algorithm for TV-L 1 Optical Flow

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL