Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2509.23393 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915519381110784 |
|---|---|
| author | Ohkawa, Takehiko Lee, Jihyun Saito, Shunsuke Saragih, Jason Prado, Fabian Xu, Yichen Yu, Shoou-I Furuta, Ryosuke Sato, Yoichi Shiratori, Takaaki |
| author_facet | Ohkawa, Takehiko Lee, Jihyun Saito, Shunsuke Saragih, Jason Prado, Fabian Xu, Yichen Yu, Shoou-I Furuta, Ryosuke Sato, Yoichi Shiratori, Takaaki |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23393 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generative Modeling of Shape-Dependent Self-Contact Human Poses Ohkawa, Takehiko Lee, Jihyun Saito, Shunsuke Saragih, Jason Prado, Fabian Xu, Yichen Yu, Shoou-I Furuta, Ryosuke Sato, Yoichi Shiratori, Takaaki Computer Vision and Pattern Recognition 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. |
| title | Generative Modeling of Shape-Dependent Self-Contact Human Poses |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.23393 |