KBody: Towards General, Robust, and Aligned Monocular Whole-Body Estimation

CVPRW 2023 pp. 6215-6225

doi:10.1109/CVPRW59228.2023.00661 /cvprw/2023/zioulis2023cvprw-kbody-a/

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. Acknowledging the importance of high quality correspondences, it leverages "virtual joints" to improve fitting performance, disentangles the optimization between the pose and shape parameters, and integrates asymmetric distance fields to strike a balance in terms of pose and shape capturing capacity, as well as pixel alignment. We also show that generative model inversion offers a strong appearance prior that can be used to complete partial human images and used as a building block for generalized and robust monocular body fitting. Project page: https://klothed.github.io/KBody.

PDF CVPRW Semantic Scholar

Cite

Text

Zioulis and O'Brien. "KBody: Towards General, Robust, and Aligned Monocular Whole-Body Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00661

Markdown

[Zioulis and O'Brien. "KBody: Towards General, Robust, and Aligned Monocular Whole-Body Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/zioulis2023cvprw-kbody-a/) doi:10.1109/CVPRW59228.2023.00661

BibTeX

@inproceedings{zioulis2023cvprw-kbody-a,
  title     = {{KBody: Towards General, Robust, and Aligned 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     = {6215-6225},
  doi       = {10.1109/CVPRW59228.2023.00661},
  url       = {https://mlanthology.org/cvprw/2023/zioulis2023cvprw-kbody-a/}
}