DMCA
Sparse Localized Deformation Components
Cached
Download Links
| Citations: | 7 - 0 self |
BibTeX
@MISC{Neumann_sparselocalized,
author = {Thomas Neumann and Kiran Varanasi and Stephan Wenger and Markus Wacker and Marcus Magnor and Christian Theobalt},
title = {Sparse Localized Deformation Components},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Figure 1: Our method automatically decomposes any mesh animations like performance captured faces (left) or muscle deformations (right) into sparse and localized deformation modes (shown in blue). Left: a new facial expression is generated by summing deformation components. Our method automatically separates spatially confined effects like separate eyebrow motions from the data. Right: Our algorithm extracts individual muscle and bone deformations. The deformation components can then be used for convenient editing of the captured animation. Here, the deformation component of the clavicle is over-exaggerated to achieve an artistically desired look. We propose a method that extracts sparse and spatially localized de-formation modes from an animated mesh sequence. To this end, we propose a new way to extend the theory of sparse matrix decom-positions to 3D mesh sequence processing, and further contribute with an automatic way to ensure spatial locality of the decompo-sition in a new optimization framework. The extracted dimensions often have an intuitive and clear interpretable meaning. Our method optionally accepts user-constraints to guide the process of discover-ing the underlying latent deformation space. The capabilities of our efficient, versatile, and easy-to-implement method are extensively demonstrated on a variety of data sets and application contexts. We demonstrate its power for user friendly intuitive editing of captured mesh animations, such as faces, full body motion, cloth animations, and muscle deformations. We further show its benefit for statisti-cal geometry processing and biomechanically meaningful anima-tion editing. It is further shown qualitatively and quantitatively that our method outperforms other unsupervised decomposition meth-ods and other animation parameterization approaches in the above use cases.
Keyphrases
sparse localized deformation component deformation component muscle deformation intuitive editing desired look convenient editing individual muscle captured animation new optimization framework animation parameterization approach use case meaningful anima-tion editing new facial expression unsupervised decomposition meth-ods cloth animation localized deformation mode statisti-cal geometry processing automatic way mesh sequence captured mesh animation mesh animation de-formation mode clear interpretable meaning separate eyebrow motion bone deformation underlying latent deformation space extracted dimension mesh sequence processing data set application context spatial locality new way easy-to-implement method full body motion
