{"ID":2864791,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23393","arxiv_id":"2509.23393","title":"Generative Modeling of Shape-Dependent Self-Contact Human Poses","abstract":"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.","short_abstract":"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-c...","url_abs":"https://arxiv.org/abs/2509.23393","url_pdf":"https://arxiv.org/pdf/2509.23393v1","authors":"[\"Takehiko Ohkawa\",\"Jihyun Lee\",\"Shunsuke Saito\",\"Jason Saragih\",\"Fabian Prado\",\"Yichen Xu\",\"Shoou-I Yu\",\"Ryosuke Furuta\",\"Yoichi Sato\",\"Takaaki Shiratori\"]","published":"2025-09-27T16:26:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}