Robust Nonrigid Registration by Convex Optimization

ICCV 2015

doi:10.1109/ICCV.2015.236 /iccv/2015/chen2015iccv-robust/

Abstract

We present an approach to nonrigid registration of 3D surfaces. We cast isometric embedding as MRF optimization and apply efficient global optimization algorithms based on linear programming relaxations. The Markov random field perspective suggests a natural connection with robust statistics and motivates robust forms of the intrinsic distortion functional. Our approach outperforms a large body of prior work by a significant margin, increasing registration precision on real data by a factor of 3.

PDF ICCV Semantic Scholar

Cite

Text

Chen and Koltun. "Robust Nonrigid Registration by Convex Optimization." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.236

Markdown

[Chen and Koltun. "Robust Nonrigid Registration by Convex Optimization." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/chen2015iccv-robust/) doi:10.1109/ICCV.2015.236

BibTeX

@inproceedings{chen2015iccv-robust,
  title     = {{Robust Nonrigid Registration by Convex Optimization}},
  author    = {Chen, Qifeng and Koltun, Vladlen},
  booktitle = {International Conference on Computer Vision},
  year      = {2015},
  doi       = {10.1109/ICCV.2015.236},
  url       = {https://mlanthology.org/iccv/2015/chen2015iccv-robust/}
}