PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence

@article{Jeon2018PARNPA,
  title={PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence},
  author={Sangryul Jeon and Seungryong Kim and Dongbo Min and Kwanghoon Sohn},
  journal={ArXiv},
  year={2018},
  volume={abs/1807.02939}
}
This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal with intra-class appearance and shape variations that commonly exist among different instances within the same object category, we leverage a pyramidal model where affine transformation fields are progressively estimated in a coarse-to-fine manner so that the smoothness constraint is… CONTINUE READING
BETA

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-3 OF 3 CITATIONS

Semantic Attribute Matching Networks

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Semantic Correspondence in the Wild

  • 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2019
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 45 REFERENCES

Convolutional Neural Network Architecture for Geometric Matching

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

DCTM: Discrete-Continuous Transformation Matching for Semantic Flow

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2017
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Proposal Flow: Semantic Correspondences from Object Proposals

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2017
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

SCNet: Learning Semantic Correspondence

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Joint Recovery of Dense Correspondence and Cosegmentation in Two Images

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

One-shot learning of object categories

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2006
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Proposal Flow

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…