← ArchivePaper2025
ASMR: Adaptive Skeleton-Mesh Rigging and Skinning via 2D Generative Prior
Sumin Hong, Soojin Choi, Chaelin Kim, Seokhyeon Cha, Junyong Noh
2D generative prior guides joint placement and skinning weight prediction for diverse skeleton and mesh configurations.
Abstract
Despite the growing accessibility of skeletal motion data, integrating it for animating character meshes remains challenging due to diverse configurations of both skeletons and meshes. Specifically, the body scale and bone lengths of the skeleton should be adjusted in accordance with the size and proportions of the mesh, ensuring that all joints are accurately positioned within the character mesh. Furthermore, defining skinning weights is complicated by variations in skeletal configurations, such as the number of joints and their hierarchy, as well as differences in mesh configurations, including their connectivity and shapes. While existing approaches have made efforts to automate this process, they hardly address the variations in both skeletal and mesh configurations. In this paper, we present a novel method for the automatic rigging and skinning of character meshes using skeletal motion data, accommodating arbitrary configurations of both meshes and skeletons. The proposed method predicts the optimal skeleton aligned with the size and proportion of the mesh as well as defines skinning weights for various meshskeleton configurations, without requiring explicit supervision tailored to each of them. By incorporating Diffusion 3D Features (Diff3F) as semantic descriptors of character meshes, our method achieves robust generalization across different configurations.
How to read this
- Category
- Method: automatic rigging and skinning
- Contributions
- Automatic rigging and skinning of character meshes from skeletal motion data across arbitrary skeleton and mesh configurations
- Predicts an optimal skeleton aligned to mesh size and proportions, positioning joints inside the mesh
- Predicts skinning weights without requiring explicit supervision, guided by a 2D generative prior
- Context
- Builds on neural rigging for articulated characters such as RigNet, extending it to handle variation in both skeletal hierarchies and mesh connectivity by leveraging a 2D generative prior.Builds on: RigNet: Neural Rigging for Articulated Characters
- Correctness
- The central claim is that a 2D generative prior can guide joint placement and weight prediction without explicit supervision across diverse configurations; readers should check what range of skeleton hierarchies and mesh topologies the method was actually evaluated on and how failure cases (badly proportioned or non-humanoid meshes) are handled.
- Clarity
- Likely accessible at the conceptual level; a first pass conveys the prior-guided idea, a second pass is needed for the joint-placement and weight formulation.
- How to read it
- First pass for the problem framing (joint-and-mesh configuration variety) and the role of the 2D prior; do a second pass if you need the actual skeleton-prediction and weight-inference formulation, and inspect the qualitative results to judge generalization.
Builds on
Built upon by
Nothing yet.
Related work
- One Model to Rig Them All: Diverse Skeleton Rigging with UniRig 2025 / SIGGRAPH
- SkinMixer: Blending 3D Animated Models 2022 / SIGGRAPH Asia
- Mobilizing Mocap, Motion Blending, and Mayhem: Rig Interoperability for Crowd Simulation on Incredibles 2 2018 / SIGGRAPH
- Automatic Rigging and Animation of 3D Characters 2007 / SIGGRAPH
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →