Feature Correspondence Via Graph Matching: Models and Global Optimization

@inproceedings{Torresani2008FeatureCV,
  title={Feature Correspondence Via Graph Matching: Models and Global Optimization},
  author={Lorenzo Torresani and Vladimir Kolmogorov and Carsten Rother},
  booktitle={ECCV},
  year={2008}
}
In this paper we present a new approach for establishing corr espondences between sparse image features related by an unknown n on-rigid mapping and corrupted by clutter and occlusion, such as points extra cted from a pair of images containing a human figure in distinct poses. We formulat e this matching task as an energy minimization problem by defining a complex objec tiv function of the appearance and the spatial arrangement of the features. Optimization of this energy is an instance of… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-10 OF 274 CITATIONS, ESTIMATED 50% COVERAGE

552 Citations

0204060'10'12'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 552 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

Feature corr espondence via graph matching: Models and global optimization

  • L. Torresani, V. Kolmogorov, C. Rother
  • Technical Report MSR-TR-2 008-101
  • 2008
Highly Influential
8 Excerpts

A decomposition method for qua dratic zero-one programming

  • P. Chardaire, A. Sutter
  • Management Science 41(4)
  • 1995
Highly Influential
5 Excerpts

Balanced graph matchi ng

  • T. Cour, P. Srinivasan, J. Shi
  • NIPS.
  • 2007
Highly Influential
4 Excerpts

Using comb inatorial optimization within maxproduct belief propagation

  • J. Duchi, D. Tarlow, G. Elidan, D. Koller
  • NIPS.
  • 2007
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…