Generalized Deformable Spatial Pyramid: Geometry-preserving dense correspondence estimation

@article{Hur2015GeneralizedDS,
  title={Generalized Deformable Spatial Pyramid: Geometry-preserving dense correspondence estimation},
  author={Junhwa Hur and Hwasup Lim and Changsoo Park and Sang Chul Ahn},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={1392-1400}
}
  • Junhwa Hur, Hwasup Lim, +1 author Sang Chul Ahn
  • Published in
    IEEE Conference on Computer…
    2015
  • Computer Science
  • We present a Generalized Deformable Spatial Pyramid (GDSP) matching algorithm for calculating the dense correspondence between a pair of images with large appearance variations. The main challenges of the problem generally originate in appearance dissimilarities and geometric variations between images. To address these challenges, we improve the existing Deformable Spatial Pyramid (DSP) [10] model by generalizing the search space and devising the spatial smoothness. The former is leveraged by… CONTINUE READING

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

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 33 CITATIONS

    Joint Recovery of Dense Correspondence and Cosegmentation in Two Images

    VIEW 12 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Discrete-Continuous Transformation Matching for Dense Semantic Correspondence

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence

    VIEW 8 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    DCTM: Discrete-Continuous Transformation Matching for Semantic Flow

    VIEW 12 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Alignment by Composition

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Semantic Matching by Weakly Supervised 2D Point Set Registration

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 23 REFERENCES

    Scale-Space SIFT flow

    VIEW 15 EXCERPTS
    HIGHLY INFLUENTIAL

    Deformable Spatial Pyramid Matching for Fast Dense Correspondences

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Dense image correspondence under large appearance variations

    VIEW 16 EXCERPTS
    HIGHLY INFLUENTIAL

    DAISY Filter Flow: A Generalized Discrete Approach to Dense Correspondences

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    SIFT Flow: Dense Correspondence across Scenes and Its Applications

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Dense Segmentation-Aware Descriptors

    VIEW 1 EXCERPT

    On SIFTs and their scales

    VIEW 2 EXCERPTS