Pose space dimensionality reduction for pose space deformation of a virtual character
Systems and methods for reducing the dimensionality of a blendshape deformation matrix. A plurality of blendshapes can be stored in an input deformation matrix. Principal components of the input deformation matrix can be determined. One or more principal components of the input deformation matrix can be omitted, leaving one or more remaining principal components. An output deformation matrix can be generated using one or more blendshapes associated with the remaining principal component(s).
1. A system comprising:
non-transitory computer storage for storing a plurality of blendshapes for a virtual character as an input deformation matrix; and
a hardware computer processor in communication with the non-transitory computer storage, the hardware computer processor being configured to reduce a dimensionality of the input deformation matrix by executing a method comprising:
determining principal components of the input deformation matrix;
omitting one or more of the principal components to leave one or more remaining principal components;
generating an output deformation matrix using one or more new blendshapes associated with the one or more remaining principal components.
2. The system of claim 1 , wherein the output deformation matrix is smaller than the input deformation matrix by a selected percentage of variation.
3. The system of claim 1 , wherein the output deformation matrix is smaller than the input deformation matrix by a selected number of blendshapes.
4. The system of claim 1 , wherein the processor method further comprises controlling a plurality of the new blendshapes in the output deformation matrix using a pose space deformer.
5. The system of claim 1 , wherein the system comprises a virtual reality, augmented reality, or mixed reality display system.
6. A method for reducing a dimensionality of an input deformation matrix which stores a plurality of blendshapes for a virtual character, the method comprising:
determining principal components of the input deformation matrix;
omitting one or more of the principal components to leave one or more remaining principal components;
generating an output deformation matrix using one or more new blendshapes associated with the one or more remaining principal components.
7. The method of claim 6 , wherein the output deformation matrix is smaller than the input deformation matrix by a selected percentage of variation.
8. The method of claim 6 , wherein the output deformation matrix is smaller than the input deformation matrix by a selected number of blendshapes.
9. The method of claim 6 , further comprising controlling a plurality of the new blendshapes in the output deformation matrix using a pose space deformer.
10. The method of claim 6 , wherein the method is carried out by a virtual reality, augmented reality, or mixed reality display system.