← ArchivePaper2014
Robust and Accurate Skeletal Rigging from Mesh Sequences
Robust skeleton extraction and skinning weight computation from mesh animation sequences using SSDR with improved stability.
Abstract
We introduce an example-based rigging approach to automatically generate linear blend skinning models with skeletal structure. Based on a set of example poses, our approach can output its skeleton, joint positions, linear blend skinning weights, and corresponding bone transformations. The output can be directly used to set up skeleton-based animation in various 3D modeling and animation software as well as game engines. Specifically, we formulate the solving of a linear blend skinning model with a skeleton as an optimization with joint constraints and weight smoothness regularization, and solve it using an iterative rigging algorithm that (i) alternatively updates skinning weights, joint locations, and bone transformations, and (ii) automatically prunes redundant bones that can be generated by an over-estimated bone initialization. Due to the automatic redundant bone pruning, our approach is more robust than existing example-based rigging approaches. Furthermore, in terms of rigging accuracy, even with a single set of parameters, our approach can soundly outperform state of the art methods on various types of experimental datasets including humans, quadrupled animals, and highly deformable models.
How to read this
- Category
- Method: example-based skeletal rigging and skinning from mesh sequences
- Contributions
- An automatic approach that outputs a skeleton, joint positions, linear blend skinning weights, and bone transformations from a set of example poses
- Formulation as an optimization with joint constraints and weight-smoothness regularization, solved by an iterative algorithm that alternates over weights, joints, and bone transforms
- Automatic pruning of redundant bones from an over-estimated initialization, improving robustness over prior example-based rigging
- Context
- Extends example-based and automatic rigging (related to Baran and Popovic's 'Automatic Rigging and Animation of 3D Characters') and the Smooth Skinning Decomposition with Rigid bones line, here with redundant-bone pruning for stability.Builds on: Automatic Rigging and Animation of 3D Characters
- Correctness
- The output is directly usable in standard DCC tools and game engines; accuracy is reported to outperform state-of-the-art methods, even with a single parameter set, across humans, quadrupeds, and highly deforming meshes, but results are bounded by the representativeness of the supplied example poses.
- Clarity
- Accessible for practitioners; a first pass conveys the LBS-with-skeleton optimization and the pruning idea, with a second pass for the alternating-update math.
- How to read it
- Read for the optimization structure (alternating weights/joints/transforms) and especially the bone-pruning mechanism that drives the robustness; second pass on the constraints and regularization if you intend to rig from your own sequences.
Builds on
Built upon by
Nothing yet.
Related work
- Smooth Skinning Decomposition with Rigid Bones 2012 / SIGGRAPH Asia
- A Statistical Model of Human Pose and Body Shape 2009 / CGF
- One Model to Rig Them All: Diverse Skeleton Rigging with UniRig 2025 / 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 →