SOMA: Unifying Parametric Human Body Models

• URL: http://arxiv.org/abs/2603.16858v1
• Date: Tue, 17 Mar 2026 17:58:03 GMT
• Title: SOMA: Unifying Parametric Human Body Models
• Abstract summary: Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible.<n>We present SOMA, a unified body layer that transforms these heterogeneous representations through three abstraction layers.<n>The entire pipeline is fully differentiable end-to-end and GPU-accelerated via NVIDIA-Warp.
• Score: 47.381120553445136
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observation [54.98864436812187]
  We propose a self-supervised framework that estimates canonical geometry, rigid part segmentation, and joint pivots, axes, and articulation states from a single RGB-D observation.<n> Experiments on synthetic and real articulated-object datasets show that our SCAPO recovers consistent part structure and accurate articulation parameters and outperforms all self-supervised baselines.
  arXiv  Detail & Related papers  (2026-06-01T09:04:49Z)
• Real-Time Human Reconstruction and Animation using Feed-Forward Gaussian Splatting [15.927245773921287]
  We present a feed-forward Gaussian splatting framework for human 3D reconstruction and real-time animation.<n>The framework operates directly on multi-view RGB images and their associated SMPL-X poses.<n>We evaluate our method on the THuman 2.1, AvatarReX and THuman 4.0 datasets.
  arXiv  Detail & Related papers  (2026-04-11T15:52:58Z)
• MORPH: Shape-agnostic PDE Foundation Models [37.26306668589026]
  MORPH is a shape-agnostic, autoregressive foundation model for partial differential equations (PDEs)<n>It is built on a convolutional vision backbone that seamlessly handles heterogeneous evaluations of varying data dimensionality (1D--3D)<n>Across extensive datasets, MORPH matches or surpasses strong baselines and recent state-of-the-art models.
  arXiv  Detail & Related papers  (2025-09-25T22:38:36Z)
• ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling [43.66748605071065]
  We present ATLAS, a high-fidelity body model learned from 600k high-resolution scans captured using 240 synchronized cameras.<n>We explicitly decouple the shape and skeleton bases by grounding our mesh representation in the human skeleton.<n> ATLAS outperforms existing methods by fitting unseen subjects in diverse poses more accurately, and quantitative evaluations show that our non-linear pose correctives more effectively capture complex poses compared to linear models.
  arXiv  Detail & Related papers  (2025-08-21T17:58:56Z)
• PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimation [5.223657684081615]
  Existing monocular 3D pose estimation methods rely on joint positional features, while overlooking intrinsic directional and angular correlations within the skeleton.<n>We propose the PoseGRAF framework to address these challenges.<n> Experimental results on the Human3.6M and MPI-INF-3DHP datasets show that our method exceeds state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-06-17T14:59:56Z)
• PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images [60.33197938330409]
  PyMAF-X is a regression-based approach to recovering parametric full-body models from monocular images. PyMAF and PyMAF-X effectively improve the mesh-image alignment and achieve new state-of-the-art results.
  arXiv  Detail & Related papers  (2022-07-13T17:58:33Z)
• NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go [109.88509362837475]
  We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes. NeuroMorph produces smooth and point-to-point correspondences between them. It works well for a large variety of input shapes, including non-isometric pairs from different object categories.
  arXiv  Detail & Related papers  (2021-06-17T12:25:44Z)
• MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency [72.82534577726334]
  We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video. Our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used, motion representation.
  arXiv  Detail & Related papers  (2020-06-22T08:50:09Z)
• Monocular Human Pose and Shape Reconstruction using Part Differentiable Rendering [53.16864661460889]
  Recent works succeed in regression-based methods which estimate parametric models directly through a deep neural network supervised by 3D ground truth. In this paper, we introduce body segmentation as critical supervision. To improve the reconstruction with part segmentation, we propose a part-level differentiable part that enables part-based models to be supervised by part segmentation.
  arXiv  Detail & Related papers  (2020-03-24T14:25:46Z)
• Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes [56.27436157101251]
  We propose a novel approach to learn human mesh reconstruction without any ground truth meshes. This is made possible by introducing two new terms into the loss function of a graph convolutional neural network (Graph CNN)
  arXiv  Detail & Related papers  (2020-02-28T20:30:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.