← ArchivePaper2016
Efficient Dynamic Skinning with Low-Rank Helper Bone Controllers
Low-rank helper bone framework efficiently captures pose-dependent skinning deformations by learning auxiliary joint transforms from examples.
Abstract
Dynamic skin deformation is vital for creating life-like characters, and its real-time computation is in great demand in interactive applications. We propose a practical method to synthesize plausible and dynamic skin deformation based on a helper bone rig. This method builds helper bone controllers for the deformations caused not only by skeleton poses but also secondary dynamics effects. We introduce a state-space model for a discrete time linear time-invariant system that efficiently maps the skeleton motion to the dynamic movement of the helper bones. Optimal transfer of nonlinear, complicated deformations, including the effect of soft-tissue dynamics, is obtained by learning the training sequence consisting of skeleton motions and corresponding skin deformations. Our approximation method for a dynamics model is highly accurate and efficient owing to its low-rank property obtained by a sparsity-oriented nuclear norm optimization. The resulting linear model is simple enough to easily implement in the existing workflows and graphics pipelines. We demonstrate the superior performance of our method compared to conventional dynamic skinning in terms of computational efficiency including LOD controls, stability in interactive controls, and flexible expression in deformations.
How to read this
- Category
- Method: dynamic skinning via low-rank helper-bone controllers
- Contributions
- Builds helper-bone controllers that reproduce skin deformation caused by both skeleton poses and secondary soft-tissue dynamics
- Introduces a state-space linear time-invariant model mapping skeleton motion to dynamic helper-bone movement, learned from training sequences of motions and deformations
- Obtains an efficient, accurate approximation through a low-rank, sparsity-oriented nuclear-norm optimization that drops into existing skinning workflows
- Context
- Extends pose-dependent deformation in the spirit of Lewis et al.'s Pose Space Deformation (lewis-psd-2000) by adding learned, dynamic helper bones with a low-rank state-space model.Builds on: Pose Space Deformation: A Unified Approach to Shape Interpolation and Skeleton-Driven Deformation
- Correctness
- Assumes complex nonlinear soft-tissue dynamics can be well approximated by a low-rank linear time-invariant helper-bone system learned from examples; accuracy and efficiency are reported as superior to conventional dynamic skinning, but the linear approximation may limit fidelity for highly nonlinear deformations outside the training data.
- Clarity
- Moderately technical; a first pass conveys the helper-bone-plus-state-space idea, a second pass covers the nuclear-norm optimization.
- How to read it
- Read first for why helper bones in a linear state-space model give real-time dynamic skinning; a second pass on the low-rank/nuclear-norm optimization if you plan to implement or extend it.
Builds on
Built upon by
Nothing yet.
Related work
- Delta Mush: Smoothing Deformations While Preserving Detail 2014 / DigiPro
- NeuroSkinning: Automatic Skin Binding for Production Characters with Deep Graph Networks 2019 / SIGGRAPH
- Data-Driven Physics for Human Soft Tissue Animation 2017 / SIGGRAPH
- A Statistical Model of Human Pose and Body Shape 2009 / CGF
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 →