ML Anthology

A New Distance for Scale-Invariant 3D Shape Recognition and Registration

Minh-Tri Pham, Oliver J. Woodford, Frank Perbet, Atsuto Maki, Björn Stenger, Roberto Cipolla
ICCV 2011 pp. 145-152
doi:10.1109/ICCV.2011.6126236 /iccv/2011/pham2011iccv-new/

Abstract

This paper presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transforms for the first time. We introduce a new distance between poses in this space-the SRT distance. It is left-invariant, unlike Euclidean distance, and has a unique, closed-form mean, in contrast to Riemannian distance, so is fast to compute. We demonstrate improved performance over the state of the art in both recognition and registration on a real and challenging dataset, by comparing our distance with others in a mean shift framework, as well as with the commonly used Hough voting approach.

ICCV Semantic Scholar

Cite

Text

Pham et al. "A New Distance for Scale-Invariant 3D Shape Recognition and Registration." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126236

Markdown

[Pham et al. "A New Distance for Scale-Invariant 3D Shape Recognition and Registration." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/pham2011iccv-new/) doi:10.1109/ICCV.2011.6126236

BibTeX

@inproceedings{pham2011iccv-new,
  title     = {{A New Distance for Scale-Invariant 3D Shape Recognition and Registration}},
  author    = {Pham, Minh-Tri and Woodford, Oliver J. and Perbet, Frank and Maki, Atsuto and Stenger, Björn and Cipolla, Roberto},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {145-152},
  doi       = {10.1109/ICCV.2011.6126236},
  url       = {https://mlanthology.org/iccv/2011/pham2011iccv-new/}
}