ML Anthology

Piecewise Image Registration in the Presence of Multiple Large Motions

Pravin Bhat, Ke Colin Zheng, Noah Snavely, Aseem Agarwala, Maneesh Agrawala, Michael F. Cohen, Brian Curless
CVPR 2006 pp. 2491-2497
doi:10.1109/CVPR.2006.225 /cvpr/2006/bhat2006cvpr-piecewise/

Abstract

We present a technique for computing a dense pixel correspondence between two images of a scene containing multiple large, rigid motions. We model each motion with either a homography (for planar objects) or a fundamental matrix. The various motions in the scene are first extracted by clustering an initial sparse set of correspondences between feature points; we then perform a multi-label graph cut optimization which assigns each pixel to an independent motion and computes its disparity with respect to that motion. We demonstrate our technique on several example scenes and compare our results with previous approaches.

CVPR Semantic Scholar

Cite

Text

Bhat et al. "Piecewise Image Registration in the Presence of Multiple Large Motions." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.225

Markdown

[Bhat et al. "Piecewise Image Registration in the Presence of Multiple Large Motions." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/bhat2006cvpr-piecewise/) doi:10.1109/CVPR.2006.225

BibTeX

@inproceedings{bhat2006cvpr-piecewise,
  title     = {{Piecewise Image Registration in the Presence of Multiple Large Motions}},
  author    = {Bhat, Pravin and Zheng, Ke Colin and Snavely, Noah and Agarwala, Aseem and Agrawala, Maneesh and Cohen, Michael F. and Curless, Brian},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {2491-2497},
  doi       = {10.1109/CVPR.2006.225},
  url       = {https://mlanthology.org/cvpr/2006/bhat2006cvpr-piecewise/}
}