A Database and Evaluation Methodology for Optical Flow

@article{Baker2007ADA,
  title={A Database and Evaluation Methodology for Optical Flow},
  author={Simon Baker and Daniel Scharstein and J. P. Lewis and Stefan Roth and Michael J. Black and Richard Szeliski},
  journal={International Journal of Computer Vision},
  year={2007},
  volume={92},
  pages={1-31}
}
  • Simon Baker, Daniel Scharstein, +3 authors Richard Szeliski
  • Published in
    IEEE 11th International…
    2007
  • Computer Science
  • International Journal of Computer Vision
  • The quantitative evaluation of optical flow algorithms by Barron et al. (1994) led to significant advances in performance. The challenges for optical flow algorithms today go beyond the datasets and evaluation methods proposed in that paper. Instead, they center on problems associated with complex natural scenes, including nonrigid motion, real sensor noise, and motion discontinuities. We propose a new set of benchmarks and evaluation methods for the next generation of optical flow algorithms… CONTINUE READING

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

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 1,643 CITATIONS

    Massively parallel Lucas Kanade optical flow for real-time video processing applications

    VIEW 16 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    A Tiny Diagnostic Dataset and Diverse Modules for Learning-Based Optical Flow Estimation

    VIEW 10 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Low Complexity, Hardware-Efficient Neighbor-Guided SGM Optical Flow for Low-Power Mobile Vision Applications

    VIEW 17 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Cubes3D: Neural Network based Optical Flow in Omnidirectional Image Scenes

    VIEW 6 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    of Copenhagen prize thesis Duality based optical flow algorithms with applications

    VIEW 16 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Real-time non-rigid target tracking for ultrasound-guided clinical interventions.

    VIEW 15 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2006
    2020

    CITATION STATISTICS

    • 323 Highly Influenced Citations

    • Averaged 151 Citations per year from 2017 through 2019

    • 10% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 28 REFERENCES

    A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

    VIEW 14 EXCERPTS

    Performance of optical flow techniques

    VIEW 15 EXCERPTS
    HIGHLY INFLUENTIAL

    High-accuracy stereo depth maps using structured light

    VIEW 7 EXCERPTS

    Learning Conditional Random Fields for Stereo

    VIEW 1 EXCERPT

    A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms

    VIEW 3 EXCERPTS

    One-shot learning of object

    • L. Fei-Fei, R. Fergus, P. Perona
    • categories. PAMI,
    • 2006
    VIEW 1 EXCERPT

    One-shot learning of object categories

    Consistent segmentation for optical flow estimation

    VIEW 1 EXCERPT