ML Anthology

3D Skeletal Reconstruction from Low-Resolution Multi-View Images

Mayank Rana, Graham W. Taylor, Ian Spiro, Christoph Bregler
CVPRW 2012 pp. 58-63
doi:10.1109/CVPRW.2012.6239238 /cvprw/2012/rana2012cvprw-3d/

Abstract

This paper demonstrates how 3D skeletal reconstruction can be performed by using a pose-sensitive embedding technique applied to multi-view video recordings. We apply our approach to challenging low-resolution video sequences. Usually skeletal reconstruction can be only achieved with many calibrated high-resolution cameras, and only blob detection can be achieved with such low-resolution imagery. We show that with this embedding technique (a metric learning technique using a deep convolutional architecture), we achieve very good 3D skeletal reconstruction on low-resolution outdoor scenes with many challenges.

CVPRW Semantic Scholar

Cite

Text

Rana et al. "3D Skeletal Reconstruction from Low-Resolution Multi-View Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012. doi:10.1109/CVPRW.2012.6239238

Markdown

[Rana et al. "3D Skeletal Reconstruction from Low-Resolution Multi-View Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012.](https://mlanthology.org/cvprw/2012/rana2012cvprw-3d/) doi:10.1109/CVPRW.2012.6239238

BibTeX

@inproceedings{rana2012cvprw-3d,
  title     = {{3D Skeletal Reconstruction from Low-Resolution Multi-View Images}},
  author    = {Rana, Mayank and Taylor, Graham W. and Spiro, Ian and Bregler, Christoph},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2012},
  pages     = {58-63},
  doi       = {10.1109/CVPRW.2012.6239238},
  url       = {https://mlanthology.org/cvprw/2012/rana2012cvprw-3d/}
}