Robust Non-Parametric Data Fitting for Correspondence Modeling

Wen-Yan Lin, Ming-Ming Cheng, Shuai Zheng, Jiangbo Lu, Nigel Crook

ICCV 2013

doi:10.1109/ICCV.2013.295 /iccv/2013/lin2013iccv-robust/

Abstract

We propose a generic method for obtaining nonparametric image warps from noisy point correspondences. Our formulation integrates a huber function into a motion coherence framework. This makes our fitting function especially robust to piecewise correspondence noise (where an image section is consistently mismatched). By utilizing over parameterized curves, we can generate realistic nonparametric image warps from very noisy correspondence. We also demonstrate how our algorithm can be used to help stitch images taken from a panning camera by warping the images onto a virtual push-broom camera imaging plane.

PDF ICCV Semantic Scholar

Cite

Text

Lin et al. "Robust Non-Parametric Data Fitting for Correspondence Modeling." International Conference on Computer Vision, 2013. doi:10.1109/ICCV.2013.295

Markdown

[Lin et al. "Robust Non-Parametric Data Fitting for Correspondence Modeling." International Conference on Computer Vision, 2013.](https://mlanthology.org/iccv/2013/lin2013iccv-robust/) doi:10.1109/ICCV.2013.295

BibTeX

@inproceedings{lin2013iccv-robust,
  title     = {{Robust Non-Parametric Data Fitting for Correspondence Modeling}},
  author    = {Lin, Wen-Yan and Cheng, Ming-Ming and Zheng, Shuai and Lu, Jiangbo and Crook, Nigel},
  booktitle = {International Conference on Computer Vision},
  year      = {2013},
  doi       = {10.1109/ICCV.2013.295},
  url       = {https://mlanthology.org/iccv/2013/lin2013iccv-robust/}
}