ML Anthology

Global Temporal Registration of Multiple Non-Rigid Surface Sequences

Peng Huang, Chris Budd, Adrian Hilton
CVPR 2011 pp. 3473-3480
doi:10.1109/CVPR.2011.5995438 /cvpr/2011/huang2011cvpr-global/

Abstract

In this paper we consider the problem of aligning multiple non-rigid surface mesh sequences into a single temporally consistent representation of the shape and motion. A global alignment graph structure is introduced which uses shape similarity to identify frames for inter-sequence registration. Graph optimisation is performed to minimise the total non-rigid deformation required to register the input sequences into a common structure. The resulting global alignment ensures that all input sequences are resampled with a common mesh structure which preserves the shape and temporal correspondence. Results demonstrate temporally consistent representation of several public databases of mesh sequences for multiple people performing a variety of motions with loose clothing and hair.

CVPR Semantic Scholar

Cite

Text

Huang et al. "Global Temporal Registration of Multiple Non-Rigid Surface Sequences." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995438

Markdown

[Huang et al. "Global Temporal Registration of Multiple Non-Rigid Surface Sequences." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/huang2011cvpr-global/) doi:10.1109/CVPR.2011.5995438

BibTeX

@inproceedings{huang2011cvpr-global,
  title     = {{Global Temporal Registration of Multiple Non-Rigid Surface Sequences}},
  author    = {Huang, Peng and Budd, Chris and Hilton, Adrian},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {3473-3480},
  doi       = {10.1109/CVPR.2011.5995438},
  url       = {https://mlanthology.org/cvpr/2011/huang2011cvpr-global/}
}