Cloth and Skin Deformation with a Triangle Mesh Based Convolutional Neural Network

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Cloth and Skin Deformation with a Triangle Mesh Based Convolutional Neural Network. / Chentanez, Nuttapong; Macklin, Miles; Müller, Matthias; Jeschke, Stefan; Kim, Tae‐yong.

In: Computer Graphics Forum, Vol. 39, No. 8, 2020, p. 123-134.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Chentanez, N, Macklin, M, Müller, M, Jeschke, S & Kim, T 2020, 'Cloth and Skin Deformation with a Triangle Mesh Based Convolutional Neural Network', Computer Graphics Forum, vol. 39, no. 8, pp. 123-134. https://doi.org/10.1111/cgf.14107

APA

Chentanez, N., Macklin, M., Müller, M., Jeschke, S., & Kim, T. (2020). Cloth and Skin Deformation with a Triangle Mesh Based Convolutional Neural Network. Computer Graphics Forum, 39(8), 123-134. https://doi.org/10.1111/cgf.14107

Vancouver

Chentanez N, Macklin M, Müller M, Jeschke S, Kim T. Cloth and Skin Deformation with a Triangle Mesh Based Convolutional Neural Network. Computer Graphics Forum. 2020;39(8):123-134. https://doi.org/10.1111/cgf.14107

Author

Chentanez, Nuttapong ; Macklin, Miles ; Müller, Matthias ; Jeschke, Stefan ; Kim, Tae‐yong. / Cloth and Skin Deformation with a Triangle Mesh Based Convolutional Neural Network. In: Computer Graphics Forum. 2020 ; Vol. 39, No. 8. pp. 123-134.

Bibtex

@article{0f9b62db7dfa4861bbf82348e6f840d7,
title = "Cloth and Skin Deformation with a Triangle Mesh Based Convolutional Neural Network",
abstract = "We introduce a triangle mesh based convolutional neural network. The proposed network structure can be used for problems where input and/or output are defined on a manifold triangle mesh with or without boundary. We demonstrate its applications in cloth upsampling, adding back details to Principal Component Analysis (PCA) compressed cloth, regressing clothing deformation from character poses, and regressing hand skin deformation from bones' joint angles. The data used for training in this work are generated from high resolution extended position based dynamics (XPBD) physics simulations with small time steps and high iteration counts and from an offline FEM simulator, but it can come from other sources. The inference time of our prototype implementation, depending on the mesh resolution and the network size, can provide between 4 to 134 times faster than a GPU based simulator. The inference also only needs to be done for meshes currently visible by the camera.",
author = "Nuttapong Chentanez and Miles Macklin and Matthias M{\"u}ller and Stefan Jeschke and Tae‐yong Kim",
year = "2020",
doi = "10.1111/cgf.14107",
language = "English",
volume = "39",
pages = "123--134",
journal = "Computer Graphics Forum",
issn = "1467-8659",
publisher = "Wiley-Blackwell",
number = "8",

}

RIS

TY - JOUR

T1 - Cloth and Skin Deformation with a Triangle Mesh Based Convolutional Neural Network

AU - Chentanez, Nuttapong

AU - Macklin, Miles

AU - Müller, Matthias

AU - Jeschke, Stefan

AU - Kim, Tae‐yong

PY - 2020

Y1 - 2020

N2 - We introduce a triangle mesh based convolutional neural network. The proposed network structure can be used for problems where input and/or output are defined on a manifold triangle mesh with or without boundary. We demonstrate its applications in cloth upsampling, adding back details to Principal Component Analysis (PCA) compressed cloth, regressing clothing deformation from character poses, and regressing hand skin deformation from bones' joint angles. The data used for training in this work are generated from high resolution extended position based dynamics (XPBD) physics simulations with small time steps and high iteration counts and from an offline FEM simulator, but it can come from other sources. The inference time of our prototype implementation, depending on the mesh resolution and the network size, can provide between 4 to 134 times faster than a GPU based simulator. The inference also only needs to be done for meshes currently visible by the camera.

AB - We introduce a triangle mesh based convolutional neural network. The proposed network structure can be used for problems where input and/or output are defined on a manifold triangle mesh with or without boundary. We demonstrate its applications in cloth upsampling, adding back details to Principal Component Analysis (PCA) compressed cloth, regressing clothing deformation from character poses, and regressing hand skin deformation from bones' joint angles. The data used for training in this work are generated from high resolution extended position based dynamics (XPBD) physics simulations with small time steps and high iteration counts and from an offline FEM simulator, but it can come from other sources. The inference time of our prototype implementation, depending on the mesh resolution and the network size, can provide between 4 to 134 times faster than a GPU based simulator. The inference also only needs to be done for meshes currently visible by the camera.

U2 - 10.1111/cgf.14107

DO - 10.1111/cgf.14107

M3 - Journal article

VL - 39

SP - 123

EP - 134

JO - Computer Graphics Forum

JF - Computer Graphics Forum

SN - 1467-8659

IS - 8

ER -

ID: 269749319