ML Anthology

Posture Invariant Surface Description and Feature Extraction

Stefanie Wuhrer, Zouhour Ben Azouz, Chang Shu
CVPR 2010 pp. 374-381
doi:10.1109/CVPR.2010.5540188 /cvpr/2010/wuhrer2010cvpr-posture/

Abstract

We propose a posture invariant surface descriptor for triangular meshes. Using intrinsic geometry, the surface is first transformed into a representation that is independent of the posture. Spin image is then adapted to derive a descriptor for the representation. The descriptor is used for extracting surface features automatically. It is invariant with respect to rigid and isometric deformations, and robust to noise and changes in resolution. The result is demonstrated by using the automatically extracted features to find correspondences between articulated meshes.

PDF CVPR Semantic Scholar

Cite

Text

Wuhrer et al. "Posture Invariant Surface Description and Feature Extraction." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5540188

Markdown

[Wuhrer et al. "Posture Invariant Surface Description and Feature Extraction." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/wuhrer2010cvpr-posture/) doi:10.1109/CVPR.2010.5540188

BibTeX

@inproceedings{wuhrer2010cvpr-posture,
  title     = {{Posture Invariant Surface Description and Feature Extraction}},
  author    = {Wuhrer, Stefanie and Azouz, Zouhour Ben and Shu, Chang},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {374-381},
  doi       = {10.1109/CVPR.2010.5540188},
  url       = {https://mlanthology.org/cvpr/2010/wuhrer2010cvpr-posture/}
}