Synthesizing cloth wrinkles by CNN-based geometry image superresolution

doi:10.1002/cav.1810

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	Synthesizing cloth wrinkles by CNN-based geometry image superresolution
	Chen, Lan 1,2; Ye, Juntao1 ; Jiang, Liguo1,2 ; Ma, Chengcheng 1,2; Cheng, Zhanglin 3; Zhang, Xiaopeng1
刊名	COMPUTER ANIMATION AND VIRTUAL WORLDS
	2018-05-01
卷号	29 期号:3-4
关键词	Cloth Animation Data-driven Deep Learning Geometry Image Wrinkle Synthesis
DOI	10.1002/cav.1810
文献子类	Article
英文摘要	We propose a novel deep learning-based method, called mesh superresolution, to enrich low-resolution (LR) cloth meshes with wrinkles. A pair of low and high-resolution (HR) meshes are simulated, with the simulation of the HR mesh tracks with that of the LR mesh. The frame data are converted into geometry images and used as a training data set. A residual network, called SR residual network, is employed to train an image synthesizer that superresolves an LR image into an HR one. Once the HR image is converted back to an HR mesh, it is abundant in wrinkles compared with its coarse counterpart. The synthesizing is very efficient and is 24x faster than a full HR simulation. We demonstrate the performances of mesh superresolution with various simulation scenes.
WOS研究方向	Computer Science
语种	英语
WOS记录号	WOS:000434083100001
资助机构	China's 863 Program(2015AA016401) ; NSFC(61502471 ; Chinese Guangdong's ST project(2017B090912001) ; 61502490)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/22055]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Chinese Acad Sci, Shenzhen Inst Adv Technol, VisuCA Key Lab, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Chen, Lan,Ye, Juntao,Jiang, Liguo,et al. Synthesizing cloth wrinkles by CNN-based geometry image superresolution[J]. COMPUTER ANIMATION AND VIRTUAL WORLDS,2018,29(3-4).
APA	Chen, Lan,Ye, Juntao,Jiang, Liguo,Ma, Chengcheng,Cheng, Zhanglin,&Zhang, Xiaopeng.(2018).Synthesizing cloth wrinkles by CNN-based geometry image superresolution.COMPUTER ANIMATION AND VIRTUAL WORLDS,29(3-4).
MLA	Chen, Lan,et al."Synthesizing cloth wrinkles by CNN-based geometry image superresolution".COMPUTER ANIMATION AND VIRTUAL WORLDS 29.3-4(2018).