Deep Deformation Detail Synthesis for Thin Shell Models

doi:10.1111/cgf.14903

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Deep Deformation Detail Synthesis for Thin Shell Models
	Chen, Lan 1,2; Gao, Lin 2,5; Yang, Jie 2,5; Xu, Shibiao 4; Ye, Juntao 1; Zhang, Xiaopeng 1; Lai, Yu-Kun 3
刊名	COMPUTER GRAPHICS FORUM
	2023-08-10
页码	13
关键词	Computing methodologies Physical simulation Artificial intelligence
ISSN号	0167-7055
DOI	10.1111/cgf.14903
通讯作者	Gao, Lin(gaolin@ict.ac.cn) ; Xu, Shibiao(shibiaoxu@bupt.edu.cn)
英文摘要	In physics-based cloth animation, rich folds and detailed wrinkles are achieved at the cost of expensive computational resources and huge labor tuning. Data-driven techniques make efforts to reduce the computation significantly by utilizing a preprocessed database. One type of methods relies on human poses to synthesize fitted garments, but these methods cannot be applied to general cloth animations. Another type of methods adds details to the coarse meshes obtained through simulation, which does not have such restrictions. However, existing works usually utilize coordinate-based representations which cannot cope with large-scale deformation, and requires dense vertex correspondences between coarse and fine meshes. Moreover, as such methods only add details, they require coarse meshes to be sufficiently close to fine meshes, which can be either impossible, or require unrealistic constraints to be applied when generating fine meshes. To address these challenges, we develop a temporally and spatially as-consistent-as-possible deformation representation (named TS-ACAP) and design a DeformTransformer network to learn the mapping from low-resolution meshes to ones with fine details. This TS-ACAP representation is designed to ensure both spatial and temporal consistency for sequential large-scale deformations from cloth animations. With this TS-ACAP representation, our DeformTransformer network first utilizes two mesh-based encoders to extract the coarse and fine features using shared convolutional kernels, respectively. To transduct the coarse features to the fine ones, we leverage the spatial and temporal Transformer network that consists of vertex-level and frame-level attention mechanisms to ensure detail enhancement and temporal coherence of the prediction. Experimental results show that our method is able to produce reliable and realistic animations in various datasets at high frame rates with superior detail synthesis abilities compared to existing methods.
资助项目	National Natural Science Foundation of China[U21A20515] ; National Natural Science Foundation of China[62171321] ; National Natural Science Foundation of China[62162044] ; National Natural Science Foundation of China[62102414] ; National Natural Science Foundation of China[62061136007] ; Beijing Municipal Natural Science Foundation for Distinguished Young Scholars[JQ21013] ; Royal Society Newton Advanced Fellowship[NAF\R2\192151] ; Innovation Funding of ICT, CAS[E361090]
WOS研究方向	Computer Science
语种	英语
出版者	WILEY
WOS记录号	WOS:001046199300001
资助机构	National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation for Distinguished Young Scholars ; Royal Society Newton Advanced Fellowship ; Innovation Funding of ICT, CAS
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53963]
专题	多模态人工智能系统全国重点实验室
通讯作者	Gao, Lin; Xu, Shibiao
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Cardiff Univ, Cardiff, Wales 4.Beijing Univ Posts & Telecommun, Beijing, Peoples R China 5.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Chen, Lan,Gao, Lin,Yang, Jie,et al. Deep Deformation Detail Synthesis for Thin Shell Models[J]. COMPUTER GRAPHICS FORUM,2023:13.
APA	Chen, Lan.,Gao, Lin.,Yang, Jie.,Xu, Shibiao.,Ye, Juntao.,...&Lai, Yu-Kun.(2023).Deep Deformation Detail Synthesis for Thin Shell Models.COMPUTER GRAPHICS FORUM,13.
MLA	Chen, Lan,et al."Deep Deformation Detail Synthesis for Thin Shell Models".COMPUTER GRAPHICS FORUM (2023):13.