DCTM: Discrete-Continuous Transformation Matching for Semantic Flow

@article{Kim2017DCTMDT,
  title={DCTM: Discrete-Continuous Transformation Matching for Semantic Flow},
  author={Seungryong Kim and D. Min and Stephen Lin and K. Sohn},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={4539-4548}
}
  • Seungryong Kim, D. Min, +1 author K. Sohn
  • Published 2017
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • Techniques for dense semantic correspondence have provided limited ability to deal with the geometric variations that commonly exist between semantically similar images. While variations due to scale and rotation have been examined, there is a lack of practical solutions for more complex deformations such as affine transformations because of the tremendous size of the associated solution space. To address this problem, we present a discrete-continuous transformation matching (DCTM) framework… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Discrete-Continuous Transformation Matching for Dense Semantic Correspondence
    4
    PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence
    18
    SFNet: Learning Object-Aware Semantic Correspondence
    10
    Learning Semantic Correspondence Exploiting an Object-level Prior
    1
    Hyperpixel Flow: Semantic Correspondence With Multi-Layer Neural Features
    15

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 64 REFERENCES
    Generalized Deformable Spatial Pyramid: Geometry-preserving dense correspondence estimation
    44
    DAISY Filter Flow: A Generalized Discrete Approach to Dense Correspondences
    76
    Universal Correspondence Network
    169
    Joint Recovery of Dense Correspondence and Cosegmentation in Two Images
    66
    FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
    37
    Non-rigid dense correspondence with applications for image enhancement
    270
    SIFT Flow: Dense Correspondence across Scenes and Its Applications
    1314
    Dense Segmentation-Aware Descriptors
    56
    Learning Dense Correspondence via 3D-Guided Cycle Consistency
    194
    Fast cost-volume filtering for visual correspondence and beyond
    782