Scale-Space SIFT flow

@article{Qiu2014ScaleSpaceSF,
  title={Scale-Space SIFT flow},
  author={Weichao Qiu and Xinggang Wang and Xiang Bai and Alan L. Yuille and Zhuowen Tu},
  journal={IEEE Winter Conference on Applications of Computer Vision},
  year={2014},
  pages={1112-1119}
}
  • Weichao Qiu, Xinggang Wang, +2 authors Zhuowen Tu
  • Published in
    IEEE Winter Conference on…
    2014
  • Computer Science
  • The state-of-the-art SIFT flow has been widely adopted for the general image matching task, especially in dealing with image pairs from similar scenes but with different object configurations. However, the way in which the dense SIFT features are computed at a fixed scale in the SIFT flow method limits its capability of dealing with scenes of large scale changes. In this paper, we propose a simple, intuitive, and very effective approach, Scale-Space SIFT flow, to deal with the large scale… 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 26 CITATIONS

    Subpixel Semantic Flow

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Generalized Deformable Spatial Pyramid: Geometry-preserving dense correspondence estimation

    VIEW 15 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Randomized Global Transformation Approach for Dense Correspondence

    VIEW 16 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Discrete-Continuous Transformation Matching for Dense Semantic Correspondence

    VIEW 7 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Alignment by Composition

    VIEW 4 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    DCTM: Discrete-Continuous Transformation Matching for Semantic Flow

    VIEW 6 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    DASC: Robust Dense Descriptor for Multi-Modal and Multi-Spectral Correspondence Estimation

    VIEW 8 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Shape-based Image Correspondence

    VIEW 7 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    A survey of variational and CNN-based optical flow techniques

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES

    On SIFTs and their scales

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    SIFT Flow: Dense Correspondence across Scenes and Its Applications

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    A Database and Evaluation Methodology for Optical Flow

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Automated colour grading using colour distribution transfer

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Factorized Graph Matching

    VIEW 1 EXCERPT

    Nonparametric Scene Parsing via Label Transfer

    VIEW 3 EXCERPTS