ML Anthology

KBody: Balanced Monocular Whole-Body Estimation

Nikolaos Zioulis, James F. O'Brien
CVPRW 2023 pp. 3540-3545
doi:10.1109/CVPRW59228.2023.00361 /cvprw/2023/zioulis2023cvprw-kbody/

Abstract

KBody is a method for fitting a low-dimensional body model to an image. It follows a predict-and-optimize approach, relying on data-driven model estimates for the constraints that will be used to solve for the body’s parameters. Compared to other approaches, it introduces virtual joints to identify higher quality correspondences and disentangles the optimization between the pose and shape parameters to achieve a more balanced result in terms of pose and shape capturing capacity, as well as pixel alignment.

CVPRW Semantic Scholar

Cite

Text

Zioulis and O'Brien. "KBody: Balanced Monocular Whole-Body Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00361

Markdown

[Zioulis and O'Brien. "KBody: Balanced Monocular Whole-Body Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/zioulis2023cvprw-kbody/) doi:10.1109/CVPRW59228.2023.00361

BibTeX

@inproceedings{zioulis2023cvprw-kbody,
  title     = {{KBody: Balanced Monocular Whole-Body Estimation}},
  author    = {Zioulis, Nikolaos and O'Brien, James F.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2023},
  pages     = {3540-3545},
  doi       = {10.1109/CVPRW59228.2023.00361},
  url       = {https://mlanthology.org/cvprw/2023/zioulis2023cvprw-kbody/}
}