SOMA: Unifying Parametric Human Body Models
2026-03-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors created SOMA, a system that connects different human body models which normally don't work well together because they use different shapes, bones, and measurements. SOMA uses three smart steps to translate any model into a common format quickly and accurately without needing complicated adjustments. This lets users mix and match body shapes and movements from different sources easily, saving time and effort. The whole process runs efficiently on GPUs, making it practical for real applications.
parametric body modelsmesh topologyskeletal structurepose abstractionskin weightingjoint transformsGPU accelerationcanonical meshSMPLmotion retargeting
Authors
Jun Saito, Jiefeng Li, Michael de Ruyter, Miguel Guerrero, Edy Lim, Ehsan Hassani, Roger Blanco Ribera, Hyejin Moon, Magdalena Dadela, Marco Di Lucca, Qiao Wang, Xueting Li, Jan Kautz, Simon Yuen, Umar Iqbal
Abstract
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.