Pose Space Deformation: A Unified Approach to Shape Interpolation and Skeleton-Driven Deformation

By John P. Lewis, Matt Cordner, Nickson Fong. International Conference on Computer Graphics and Interactive Techniques, 2000

1,069 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/94d88e179a187aee3a5418c7e288e1a317c0b109

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

As-rigid-as-possible shape manipulation (2005, methodology): “With skeletons, each point in the shape is associated with a coordinate frame defined by a bone [Lewis et al. 2000].”
Neural volumes (2019, background): “This can be viewed as an extension of linear blend skinning [Lewis et al. 2000] applied to a volumetric space.”
Curve skeleton extraction from incomplete point cloud (2009, methodology): “2008], animation [Lewis et al. 2000], and shape matching [Hilaga et al.”
SCAPE: shape completion and animation of people (2005, methodology): “A popular animation approach called skinning (described in [Lewis et al. 2000]) assumes that the point displacements are generated by a weighted set of (usually linear) influences from neighboring joints.”
Fake it till you make it: face analysis in the wild using synthetic data alone (2021, background): “where L(X, ~ θ,J;W) is a standard linear blend skinning (LBS) function [33] that rotates vertex positions X ∈ RN×3 about joint locations J ∈ RK×3 by local joint rotations ~ θ, with per-vertex weights W ∈ RK×N determining how rotations are interpolated across the mesh.”
STAR: Sparse Trained Articulated Human Body Regressor (2020, methodology): “Lewis [19] introduces the pose space deformation model (PSD) where LBS is complemented with corrective deformations.”
Hierarchical mesh decomposition using fuzzy clustering and cuts (2003, methodology): “Finally, to pose the object, a skeleton-subspace deformation method is used [Lewis et al. 2000].”
Hierarchical mesh segmentation based on fitting primitives (2006, methodology): “Once the skeleton is available, vertices can be attached to influencing joints, and their position after a deformation can be computed as described in [ 12 ].”
Articulation-Aware Canonical Surface Mapping (2020, methodology): “While our initial grouping is discrete, following standard practices in computer graphics [19], we ‘soften’ the per-vertex assignment as depicted in Figure 2.”
Efficient elasticity for character skinning with contact and collisions (2011, background): “Instead, such phenomena are typically created through a variety of example based approaches [Lewis et al. 2000; Sloan et al. 2001].”
3D hand tracking by rapid stochastic gradient descent using a skinning model (2004, methodology): “Such model gives us a higher accuracy in the reproduction of actual hand shapes, and hence also better supports tracking by producing more subtle effects like the deformation of the palm.”
Parsing the Hand in Depth Images (2014, methodology): “Give a hypothesized hand pose , the joint positions of the skeleton are first computed using forward kinematics, and the positions of the vertices on the skin mesh are then updated using the skeleton subspace deformation method [13].”
Subspace gradient domain mesh deformation (2006, methodology): “These artifacts can be greatly reduced by accurate anatomical simulation [Wilhelms and Gelder 1997] or by example-based synthesis [Lewis et al. 2000; Kry et al. 2002; Sumner et al. 2005].”