← ArchivePaper2012
Smooth Skinning Decomposition with Rigid Bones
SSDR: automatically extracting bone transforms and weights from example animations, widely used for rig conversion and crowd pipelines.
Abstract
This paper introduces the Smooth Skinning Decomposition with Rigid Bones (SSDR), an automated algorithm to extract the linear blend skinning (LBS) from a set of example poses. The SSDR model can effectively approximate the skin deformation of nearly articulated models as well as highly deformable models by a low number of rigid bones and a sparse, convex bone-vertex weight map. Formulated as a constrained optimization problem where the least squared error of the reconstructed vertices by LBS is minimized, the SSDR model can be solved by a block coordinate descent-based algorithm to iteratively update the weight map and the bone transformations. By employing the sparseness and convex constraints on the weight map, the SSDR model can be used for traditional skinning decomposition tasks such as animation compression and hardware-accelerated rendering. Moreover, by imposing the orthogonal constraints on the bone rotation matrices (rigid bones), the SSDR model can also be applied in motion editing, skeleton extraction, and collision detection tasks. Through qualitative and quantitative evaluations, we show the SSDR model can measurably outperform the state-of-the-art skinning decomposition schemes in terms of accuracy and applicability.
How to read this
- Category
- Method: skinning decomposition algorithm
- Contributions
- SSDR: automatically extracts linear blend skinning (bone transforms and a weight map) from a set of example poses
- Solves a constrained least-squares reconstruction via block coordinate descent that alternately updates weights and bone transformations
- Enforces sparse, convex weights and orthogonal (rigid) bone rotations, enabling compression, hardware skinning, skeleton extraction, motion editing, and collision tasks
- Context
- Builds on pose-space and example-driven skinning lineage (Lewis et al. Pose Space Deformation, James and Twigg Skinning Mesh Animations), targeting an LBS-compatible decomposition.Builds on: Pose Space Deformation: A Unified Approach to Shape Interpolation and Skeleton-Driven Deformation · Skinning Mesh Animations
- Correctness
- Validated qualitatively and quantitatively against prior skinning-decomposition methods on articulated and highly deformable models; quality hinges on the number of bones chosen and how representative the example poses are, and block coordinate descent gives a local optimum.
- Clarity
- Accessible; a first pass conveys the LBS-fitting goal and the alternating solve, a second pass clarifies the constraint handling and convergence.
- How to read it
- Read for the optimization setup (objective, sparsity and rigidity constraints, alternating update); a second pass pays off if you plan to reimplement or tune bone count for a rig-conversion or crowd pipeline.
Builds on
Related work
- Two-Layer Sparse Compression of Dense-Weight Blend Skinning 2013 / SIGGRAPH
- Robust and Accurate Skeletal Rigging from Mesh Sequences 2014 / SIGGRAPH
- Fast Automatic Skinning Transformations 2012 / SIGGRAPH
- Direct Delta Mush Skinning Compression with Continuous Examples 2021 / 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 →