SOMA: Unifying Parametric Human Body Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912971244961792 |
|---|---|
| author | Saito, Jun Li, Jiefeng de Ruyter, Michael Guerrero, Miguel Lim, Edy Hassani, Ehsan Ribera, Roger Blanco Moon, Hyejin Dadela, Magdalena Di Lucca, Marco Wang, Qiao Li, Xueting Kautz, Jan Yuen, Simon Iqbal, Umar |
| author_facet | Saito, Jun Li, Jiefeng de Ruyter, Michael Guerrero, Miguel Lim, Edy Hassani, Ehsan Ribera, Roger Blanco Moon, Hyejin Dadela, Magdalena Di Lucca, Marco Wang, Qiao Li, Xueting Kautz, Jan Yuen, Simon Iqbal, Umar |
| contents | Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible: SMPL, SMPL-X, MHR, Anny, and related models each diverge in mesh topology, skeletal structure, shape parameterization, and unit convention, making it impractical to exploit their complementary strengths within a single pipeline. We present SOMA, a unified body layer that bridges these heterogeneous representations through three abstraction layers. Mesh topology abstraction maps any source model's identity to a shared canonical mesh in constant time per vertex. Skeletal abstraction recovers a full set of identity-adapted joint transforms from any body shape, whether in rest pose or an arbitrary posed configuration, in a single closed-form pass, with no iterative optimization or per-model training. Pose abstraction inverts the skinning pipeline to recover unified skeleton rotations directly from posed vertices of any supported model, enabling heterogeneous motion datasets to be consumed without custom retargeting. Together, these layers reduce the $O(M^2)$ per-pair adapter problem to $O(M)$ single-backend connectors, letting practitioners freely mix identity sources and pose data at inference time. The entire pipeline is fully differentiable end-to-end and GPU-accelerated via NVIDIA-Warp. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16858 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SOMA: Unifying Parametric Human Body Models Saito, Jun Li, Jiefeng de Ruyter, Michael Guerrero, Miguel Lim, Edy Hassani, Ehsan Ribera, Roger Blanco Moon, Hyejin Dadela, Magdalena Di Lucca, Marco Wang, Qiao Li, Xueting Kautz, Jan Yuen, Simon Iqbal, Umar Computer Vision and Pattern Recognition Artificial Intelligence Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible: SMPL, SMPL-X, MHR, Anny, and related models each diverge in mesh topology, skeletal structure, shape parameterization, and unit convention, making it impractical to exploit their complementary strengths within a single pipeline. We present SOMA, a unified body layer that bridges these heterogeneous representations through three abstraction layers. Mesh topology abstraction maps any source model's identity to a shared canonical mesh in constant time per vertex. Skeletal abstraction recovers a full set of identity-adapted joint transforms from any body shape, whether in rest pose or an arbitrary posed configuration, in a single closed-form pass, with no iterative optimization or per-model training. Pose abstraction inverts the skinning pipeline to recover unified skeleton rotations directly from posed vertices of any supported model, enabling heterogeneous motion datasets to be consumed without custom retargeting. Together, these layers reduce the $O(M^2)$ per-pair adapter problem to $O(M)$ single-backend connectors, letting practitioners freely mix identity sources and pose data at inference time. The entire pipeline is fully differentiable end-to-end and GPU-accelerated via NVIDIA-Warp. |
| title | SOMA: Unifying Parametric Human Body Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.16858 |