Dual-Feature Warping-Based Motion Model Estimation

@article{Li2015DualFeatureWM,
  title={Dual-Feature Warping-Based Motion Model Estimation},
  author={Shiwei Li and Lu Yuan and Jian Sun and Long Quan},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={4283-4291}
}
To break down the geometry assumptions of traditional motion models (e.g., homography, affine), warping-based motion model recently becomes very popular and is adopted in many latest applications (e.g., image stitching, video stabilization). With high degrees of freedom, the accuracy of model heavily relies on data-terms (keypoint correspondences). In some low-texture environments (e.g., indoor) where keypoint feature is insufficient or unreliable, the warping model is often erroneously… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 14 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 31 references

Homography estimation

  • E. Dubrofsky
  • PhD thesis, UNI- VERSITY OF BRITISH COLUMBIA…
  • 2009
Highly Influential
5 Excerpts

Similar Papers

Loading similar papers…