← ArchivePaper2006
Real-Time Weighted Pose-Space Deformation on the GPU
GPU-parallel example-based pose-space deformation that automatically computes per-vertex blend weights from sample poses.
Abstract
WPSD (Weighted Pose Space Deformation) is an example based skinning method for articulated body animation. The per‐vertex computation required in WPSD can be parallelized in a SIMD (Single Instruction Multiple Data) manner and implemented on a GPU. While such vertex‐parallel computation is often done on the GPU vertex processors, further parallelism can potentially be obtained by using the fragment processors. In this paper, we develop a parallel deformation method using the GPU fragment processors. Joint weights for each vertex are automatically calculated from sample poses, thereby reducing manual effort and enhancing the quality of WPSD as well as SSD (Skeletal Subspace Deformation). We show sufficient speed‐up of SSD, PSD (Pose Space Deformation) and WPSD to make them suitable for real‐time applications . Categories and Subject Descriptors (according to ACM CCS): I.3.1 [Computer Graphics]: Hardware Architecture‐Parallel processing, I.3.5 [Computer Graphics]: Computational Geometry and Object Modeling‐Curve, surface, solid and object modeling, I.3.7 [Computer Graphics]: Three‐Dimensional Graphics and Realism‐Animation.
How to read this
- Category
- Method: GPU example-based skinning (weighted pose-space deformation)
- Contributions
- A parallel WPSD deformation method that exploits GPU fragment processors for additional parallelism beyond vertex processors.
- Automatic per-vertex joint weight computation from sample poses, reducing manual rigging effort.
- Real-time speed-ups for SSD, PSD and WPSD, making example-based skinning suitable for interactive applications.
- Context
- Builds directly on Lewis et al.'s Pose Space Deformation, adding automatic weighting and a GPU (fragment-processor) parallelization of the per-vertex computation.Builds on: Pose Space Deformation: A Unified Approach to Shape Interpolation and Skeleton-Driven Deformation
- Correctness
- Validated as a speed and quality improvement on articulated body animation; gains are reported on the era's GPU fragment-processor architecture, so the specific performance argument is hardware-dependent and the deformation quality still relies on representative sample poses.
- Clarity
- Accessible if you already know SSD/PSD; a first pass conveys the GPU-parallel WPSD idea, a second pass for the weight-computation and fragment-processor mapping.
- How to read it
- First pass for the why (auto weights plus GPU parallelism); second pass on the fragment-processor data layout only if GPU implementation detail matters to you, otherwise the conceptual contribution suffices.
Builds on
Related work
- EigenSkin: Real Time Large Deformation Character Skinning in Hardware 2002 / SCA
- Scan-based Volume Animation Driven by Locally Adaptive Articulated Registrations 2011 / TVCG
- Mobilizing Mocap, Motion Blending, and Mayhem: Rig Interoperability for Crowd Simulation on Incredibles 2 2018 / SIGGRAPH
- Dyna: A Model of Dynamic Human Shape in Motion 2015 / 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 →