One can hardly model self-contact of human poses without considering underlying body shapes. For example, the pose of rubbing a belly for a person with a low BMI leads to penetration of the hand into the belly for a person with a high BMI. Despite its relevance, existing self-contact datasets lack the variety of self-contact poses and precise body shapes, limiting conclusive analysis between self-contact poses and shapes. To address this, we begin by introducing the first extensive self-contact dataset with precise body shape registration, Goliath-SC, consisting of 383K self-contact poses across 130 subjects. Using this dataset, we propose generative modeling of self-contact prior conditioned by body shape parameters, based on a body-part-wise latent diffusion with self-attention. We further incorporate this prior into single-view human pose estimation while refining estimated poses to be in contact. Our experiments suggest that shape conditioning is vital to the successful modeling of self-contact pose distribution, hence improving single-view pose estimation in self-contact.
Cite
@article{arxiv.2509.23393,
title = {Generative Modeling of Shape-Dependent Self-Contact Human Poses},
author = {Takehiko Ohkawa and Jihyun Lee and Shunsuke Saito and Jason Saragih and Fabian Prado and Yichen Xu and Shoou-I Yu and Ryosuke Furuta and Yoichi Sato and Takaaki Shiratori},
journal= {arXiv preprint arXiv:2509.23393},
year = {2025}
}
Comments
Accepted to ICCV 2025. Project page: https://tkhkaeio.github.io/projects/25-scgen