Real-time C2-Weighting Based Character Skinning Powered by GPU

Chuhua Xian; Junxian Huang; Shuo Jin; Guoliang  Luo; Charlie Wang

Real-time C2-Weighting Based Character Skinning Powered by GPU

Chuhua Xian, Junxian Huang, Shuo Jin, Guoliang Luo, Charlie Wang

Materials and Manufacturing

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Abstract

Handle driven character skinning is widely favored in animation applications due to its advantages of intuitiveness, effectiveness and simplicity. A research thread to realize this is to compute a proper weighting distribution on points associated with specified handles like points, bars or skeleton, which is critical to the quality of manipulation and can be utilized to produce animation by controlling
user handles. In this work, we introduce a new skinning method that is compatible with different model representations, with a key idea of evaluating the local influence of each handle by decomposing the shape domain into small
overlapped regions. Thanks to its well-designed formulation, the computation of weights and update of models can be conducted in par-allel on GPU, leading to high efficiency and good visual quality supported by the provided experimental and statistical results in this paper.

Original language	English
Title of host publication	Proceedings of the 30th International Conference on Computer Animation and Social Agents
Publisher	KAIST
Pages	11-14
Number of pages	4
ISBN (Print)	978-89-89453-82-6
Publication status	Published - 2017
Event	CASA 17 : The 30th International Conference on Computer Animation and Social Agents - Seoul, Korea, Republic of Duration: 22 May 2017 → 24 May 2017

Conference

Conference	CASA 17
Country/Territory	Korea, Republic of
City	Seoul
Period	22/05/17 → 24/05/17

Keywords

real-time skinning
linear blending
region decomposition
GPU

Cite this

@inproceedings{f1911061cef94eb183ec3a4d353bf4fe,

title = "Real-time C2-Weighting Based Character Skinning Powered by GPU",

abstract = "Handle driven character skinning is widely favored in animation applications due to its advantages of intuitiveness, effectiveness and simplicity. A research thread to realize this is to compute a proper weighting distribution on points associated with specified handles like points, bars or skeleton, which is critical to the quality of manipulation and can be utilized to produce animation by controllinguser handles. In this work, we introduce a new skinning method that is compatible with different model representations, with a key idea of evaluating the local influence of each handle by decomposing the shape domain into smalloverlapped regions. Thanks to its well-designed formulation, the computation of weights and update of models can be conducted in par-allel on GPU, leading to high efficiency and good visual quality supported by the provided experimental and statistical results in this paper.",

keywords = "real-time skinning, linear blending, region decomposition, GPU",

author = "Chuhua Xian and Junxian Huang and Shuo Jin and Guoliang Luo and Charlie Wang",

year = "2017",

language = "English",

isbn = "978-89-89453-82-6",

pages = "11--14",

booktitle = "Proceedings of the 30th International Conference on Computer Animation and Social Agents",

publisher = "KAIST",

note = "CASA 17 : The 30th International Conference on Computer Animation and Social Agents ; Conference date: 22-05-2017 Through 24-05-2017",

}

Real-time C2-Weighting Based Character Skinning Powered by GPU. / Xian, Chuhua; Huang, Junxian; Jin, Shuo; Luo, Guoliang ; Wang, Charlie.

Proceedings of the 30th International Conference on Computer Animation and Social Agents. KAIST, 2017. p. 11-14.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Real-time C2-Weighting Based Character Skinning Powered by GPU

AU - Xian, Chuhua

AU - Huang, Junxian

AU - Jin, Shuo

AU - Luo, Guoliang

AU - Wang, Charlie

PY - 2017

Y1 - 2017

N2 - Handle driven character skinning is widely favored in animation applications due to its advantages of intuitiveness, effectiveness and simplicity. A research thread to realize this is to compute a proper weighting distribution on points associated with specified handles like points, bars or skeleton, which is critical to the quality of manipulation and can be utilized to produce animation by controllinguser handles. In this work, we introduce a new skinning method that is compatible with different model representations, with a key idea of evaluating the local influence of each handle by decomposing the shape domain into smalloverlapped regions. Thanks to its well-designed formulation, the computation of weights and update of models can be conducted in par-allel on GPU, leading to high efficiency and good visual quality supported by the provided experimental and statistical results in this paper.

AB - Handle driven character skinning is widely favored in animation applications due to its advantages of intuitiveness, effectiveness and simplicity. A research thread to realize this is to compute a proper weighting distribution on points associated with specified handles like points, bars or skeleton, which is critical to the quality of manipulation and can be utilized to produce animation by controllinguser handles. In this work, we introduce a new skinning method that is compatible with different model representations, with a key idea of evaluating the local influence of each handle by decomposing the shape domain into smalloverlapped regions. Thanks to its well-designed formulation, the computation of weights and update of models can be conducted in par-allel on GPU, leading to high efficiency and good visual quality supported by the provided experimental and statistical results in this paper.

KW - real-time skinning

KW - linear blending

KW - region decomposition

KW - GPU

UR - https://casa2017.kaist.ac.kr/wordpress/

M3 - Conference contribution

SN - 978-89-89453-82-6

SP - 11

EP - 14

BT - Proceedings of the 30th International Conference on Computer Animation and Social Agents

PB - KAIST

T2 - CASA 17

Y2 - 22 May 2017 through 24 May 2017

ER -

Real-time C2-Weighting Based Character Skinning Powered by GPU

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this