Data-driven weight optimization for real-time mesh deformation

doi:10.1016/j.gmod.2019.101037

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Data-driven weight optimization for real-time mesh deformation
	Yuan, Yu-Jie 1,2; Lai, Yu-Kun 3; Wu, Tong 1; Xia, Shihong 1; Gao, Lin 1
刊名	GRAPHICAL MODELS
	2019-07-01
卷号	104 页码:10
关键词	Real-time mesh deformation Biharmonic weights Data-driven As-rigid-as-possible
ISSN号	1524-0703
DOI	10.1016/j.gmod.2019.101037
英文摘要	3D model deformation has been an active research topic in geometric processing. Due to its efficiency, linear blend skinning (LBS) and its follow-up methods are widely used in practical applications as an efficient method for deforming vector images, geometric models and animated characters. LBS needs to determine the control handles and specify their influence weights, which requires expertise and is time-consuming. Further studies have proposed a method for efficiently calculating bounded biharmonic weights of given control handles which reduces user effort and produces smooth deformation results. The algorithm defines a high-order shape-aware smoothness function which tends to produce smooth deformation results, but fails to generate locally rigid deformations. To address this, we propose a novel data-driven approach to producing improved weights for handles that makes full use of available 3D model data by optimizing an energy consisting of data-driven, rigidity and sparsity terms, while maintaining its advantage of allowing handles of various forms. We further devise an efficient iterative optimization scheme. Through contrast experiments, it clearly shows that linear blend skinning based on our optimized weights better reflects the deformation characteristics of the model, leading to more accurate deformation results, outperforming existing methods. The method also retains real-time performance even with a large number of deformation examples. Our ablation experiments also show that each energy term is essential.
资助项目	National Natural Science Foundation of China[61872440] ; National Natural Science Foundation of China[61828204] ; Beijing Natural Science Foundation[L182016] ; Young Elite Scientists Sponsorship Program by CAST[2017QNRC001] ; Youth Innovation Promotion Association CAS ; Huawei HIRP Open Fund[HO2018085141] ; CCF-Tencent Open Fund ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR)[201900055] ; SenseTime Research Fund
WOS研究方向	Computer Science
语种	英语
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
WOS记录号	WOS:000477696600007
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/4492]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Gao, Lin
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Cardiff Univ, Sch Comp Sci & Informat, Cardiff, S Glam, Wales
推荐引用方式 GB/T 7714	Yuan, Yu-Jie,Lai, Yu-Kun,Wu, Tong,et al. Data-driven weight optimization for real-time mesh deformation[J]. GRAPHICAL MODELS,2019,104:10.
APA	Yuan, Yu-Jie,Lai, Yu-Kun,Wu, Tong,Xia, Shihong,&Gao, Lin.(2019).Data-driven weight optimization for real-time mesh deformation.GRAPHICAL MODELS,104,10.
MLA	Yuan, Yu-Jie,et al."Data-driven weight optimization for real-time mesh deformation".GRAPHICAL MODELS 104(2019):10.