Traditional Linear Blend Skinning (LBS) often fails under complex deformations and joint constraints.
PhysRig introduces a fully physics-based rigging solution with:
Figure 1. PhysRig models articulated objects as soft-body volumes driven by embedded control points, enabling realistic deformations and dynamics across diverse topologies—from humanoids to dinosaurs.
Skinning and rigging are fundamental components in animation, articulated object reconstruction, motion transfer, and 4D generation. Existing approaches predominantly rely on Linear Blend Skinning (LBS), due to its simplicity and differentiability. However, LBS introduces artifacts such as volume loss and unnatural deformations, and it fails to model elastic materials like soft tissues, fur, and flexible appendages (e.g., elephant trunks, ears, and fatty tissues).
In this work, we propose PhysRig: a differentiable physics-based skinning and rigging framework that overcomes these limitations by embedding the rigid skeleton into a volumetric representation (e.g., a tetrahedral mesh), which is simulated as a deformable soft-body structure driven by the animated skeleton. Our method leverages continuum mechanics and discretizes the object as particles embedded in an Eulerian background grid to ensure differentiability with respect to both material properties and skeletal motion.
Additionally, we introduce material prototypes, significantly reducing the learning space while maintaining high expressiveness. To evaluate our framework, we construct a comprehensive synthetic dataset using meshes from Objaverse, The Amazing Animals Zoo, and Mixamo, covering diverse object categories and motion patterns. Our method consistently outperforms traditional LBS-based approaches, generating more realistic and physically plausible results. Furthermore, we demonstrate the applicability of our framework in the pose transfer task, highlighting its versatility for articulated object modeling.
Figure 2. Overview of PhysRig. Given a 3D object, we first compute coarse skinning weights, which initialize embedded driving points for local deformation control. These points, assigned velocities, are linked to an elastic 3D volume with material parameters governing deformation. The differentiable physics-based skinning module generates natural deformations, optimizing velocities and material properties via backward propagation. Finally, multi-view animations illustrate physically plausible shape deformations over time.
Figure 3. PhysRig enables pose transfer for generated objects.
Figure 4. Animation results from the PhysRig approach. These results are obtained from the inverse skinning problem by optimizing material properties and driving point velocities to minimize the deviation from the ground truth mesh sequence.
Figure 5. Comparison of the learned material properties with ground truth using our method.
Figure 6. Qualitative comparisons of PhysRig and neural linear blend skinning using ground truth skinning weights as initialization.
Figure 7. Visualization of material prototype centers learned by PhysRig.
PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling
@misc{zhang2025physrigdifferentiablephysicsbasedskinning,
title={PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling},
author={Hao Zhang and Haolan Xu and Chun Feng and Varun Jampani and Narendra Ahuja},
year={2025},
eprint={2506.20936},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2506.20936},
}