Fast and Efficient Skinning of Animated Meshes

Kavan, Ladislav; Sloan, Peter-Pike; O’Sullivan, Carol

doi:10.1111/j.1467-8659.2009.01602.x

Cited by 86 publications

(101 citation statements)

References 45 publications

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…We also compare to skinning decomposition methods that learn explicit bone transformations, especially to the method of [Kavan et al 2010]. We observed two key problems which interfere with the target applications that our method is designed for.…”

Section: Facial Performancesmentioning

confidence: 99%

“…For each of the remaining frames, we randomly selected sparse control points on the mesh and reconstructed the weights for the components to fit only to the control points. We compare the resulting complete mesh to the ground truth and again (a) Skinning Decomposition [Kavan et al 2010], from left to right: Vertex influences; Influence and motion of 2 bones in isolation; silencing the motions of all but one bone gives artifacts; bones offer too many degrees of freedom, e.g. arbitrary translation of the lip which results in artifacts.…”

Section: Quantitative Evaluationmentioning

confidence: 99%

“…use the error metric from [Kavan et al 2010]. The experiment was repeated in 5 trials differing in training set, each trial was further repeated 10 times using different random control points.…”

Section: Quantitative Evaluationmentioning

confidence: 99%

“…To reconstruct the training set, we invert Eq. (1) and measure the difference in vertex coordinates with the error metric introduced in [Kavan et al 2010] (root mean squared error multiplied by 1000 for convenience). The averaged reconstruction errors over 3 different random splits are reported in Fig.…”

Section: Quantitative Evaluationmentioning

confidence: 99%

“…Such skeletons often miss detail that can be re-introduced in pose space using the Eigenskin method [Kry et al 2000], which essentially comes down to clustered PCA (with overlapping regions) and linear regression in pose space, and only works given sufficient training data. More general skinning decomposition methods fit unordered non-hierarchical collections of arbitrary [Kavan et al 2010] or rigid [Le and Deng 2012] bone transformations and blend weights to mesh animations. While useful for quick rendering using GPU's, this is not so useful for editing -the bones offer many degrees of freedom that quickly produce deformations far outside the input range.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Sparse localized deformation components

et al. 2013

View full text Add to dashboard Cite

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. AbstractWe propose a method that extracts sparse and spatially localized deformation modes from an animated mesh sequence. To this end, we propose a new way to extend the theory of sparse matrix decompositions to 3D mesh sequence processing, and further contribute with an automatic way to ensure spatial locality of the decomposition 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 discovering 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 statistical geometry processing and biomechanically meaningful animation editing. It is further shown qualitatively and quantitatively that our method outperforms other unsupervised decomposition methods and other animation parameterization approaches in the above use cases.

show abstract

Section: Facial Performancesmentioning

confidence: 99%

Section: Quantitative Evaluationmentioning

confidence: 99%

Section: Quantitative Evaluationmentioning

confidence: 99%

Section: Quantitative Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Sparse localized deformation components

et al. 2013

View full text Add to dashboard Cite

show abstract

Pose space parameterization and style transfer of skin deformation

Kim

Choi

Hoffmann

2011

Computer Animation & Virtual

View full text Add to dashboard Cite

We present a technique to parameterize skin deformation by skeletal motion and to transfer the deformation style from one character to another. We decompose skin deformation into time-varying signals and basis matrices by using dimension reduction techniques and then approximate the time-varying signals by using radial basis functions with respect to joint angles that define skeletal motion. This decomposition reduces the size of deformation data to a small number of time-varying signals that represent the complex role of muscle action. The subsequent parameterization yields a fast and intuitive control of characters; thus, it allows us to construct faithful skin deformations quickly as skeletal bones move. The representation of our parameterization allows us to capture and transfer a derived deformation style to another skeletonskin structure without considering the input dimension of the deformation data. This style transfer can be used as a basis for realistically animating variants of sample characters that have the same skeletal topology. Parameterization of skin deformation and its style transfer can be performed within a small amount of error once the preprocessing time and control of the deformation is carried out in real time by our graphics processing unit implementation.

show abstract

A Brush Stroke Synthesis Toolbox

DiVerdi

2012

Computational Imaging and Vision

View full text Add to dashboard Cite

Fast and Efficient Skinning of Animated Meshes

Abstract: Skinning is a simple yet popular deformation

Cited by 86 publications

References 45 publications

Sparse localized deformation components

Sparse localized deformation components

Pose space parameterization and style transfer of skin deformation

A Brush Stroke Synthesis Toolbox

Contact Info

Product

Resources

About