KBody: Balanced Monocular Whole-Body Estimation

Nikolaos Zioulis, James F. O'Brien; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 3540-3545

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.

Related Material

[pdf] [supp]
[bibtex]
@InProceedings{Zioulis_2023_CVPR, author = {Zioulis, Nikolaos and O'Brien, James F.}, title = {KBody: Balanced Monocular Whole-Body Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {3540-3545} }