Sparse Data Driven Mesh Deformation

doi:10.1109/TVCG.2019.2941200

	Sparse Data Driven Mesh Deformation
	Gao, Lin 2; Lai, Yu-Kun 1; Yang, Jie 2; Zhang, Ling-Xiao 2; Xia, Shihong 2; Kobbelt, Leif 3
刊名	IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
	2021-03-01
卷号	27 期号:3 页码:2085-2100
关键词	Strain Shape Deformable models Interpolation Computational modeling Geometry Manifolds Data driven sparsity large scale deformation real-time deformation
ISSN号	1077-2626
DOI	10.1109/TVCG.2019.2941200
英文摘要	Example-based mesh deformation methods are powerful tools for realistic shape editing. However, existing techniques typically combine all the example deformation modes, which can lead to overfitting, i.e., using an overly complicated model to explain the user-specified deformation. This leads to implausible or unstable deformation results, including unexpected global changes outside the region of interest. To address this fundamental limitation, we propose a sparse blending method that automatically selects a smaller number of deformation modes to compactly describe the desired deformation. This along with a suitably chosen deformation basis including spatially localized deformation modes leads to significant advantages, including more meaningful, reliable, and efficient deformations because fewer and localized deformation modes are applied. To cope with large rotations, we develop a simple but effective representation based on polar decomposition of deformation gradients, which resolves the ambiguity of large global rotations using an as-consistent-as-possible global optimization. This simple representation has a closed form solution for derivatives, making it efficient for our sparse localized representation and thus ensuring interactive performance. Experimental results show that our method outperforms state-of-the-art data-driven mesh deformation methods, for both quality of results and efficiency.
资助项目	Beijing Municipal Natural Science Foundation[L182016] ; National Natural Science Foundation of China[61872440] ; National Natural Science Foundation of China[61828204] ; Youth Innovation Promotion Association CAS ; Young Elite Scientists Sponsorship Program by CAST[2017QNRC001] ; CCF-Tencent Open Fund ; SenseTime Research Fund ; Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University[VRLAB2019C01]
WOS研究方向	Computer Science
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000613744500016
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/16257]
专题	中国科学院计算技术研究所
通讯作者	Gao, Lin
作者单位	1.Cardiff Univ, Sch Comp Sci & Informat, Visual Comp Grp, Cardiff CF10 3AT, Wales 2.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China 3.Rhein Westfal TH Aachen, Inst Comp Graph & Multimedia, D-52062 Aachen, Germany
推荐引用方式 GB/T 7714	Gao, Lin,Lai, Yu-Kun,Yang, Jie,et al. Sparse Data Driven Mesh Deformation[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2021,27(3):2085-2100.
APA	Gao, Lin,Lai, Yu-Kun,Yang, Jie,Zhang, Ling-Xiao,Xia, Shihong,&Kobbelt, Leif.(2021).Sparse Data Driven Mesh Deformation.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,27(3),2085-2100.
MLA	Gao, Lin,et al."Sparse Data Driven Mesh Deformation".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 27.3(2021):2085-2100.