Fragmentation Guided Human Shape Reconstruction

doi:10.1109/ACCESS.2019.2905879

	Fragmentation Guided Human Shape Reconstruction
	Yingliang Zhang 1; Xi Luo 2; Wei Yang 2; Jingyi Yu3
	2019
发表期刊	IEEE ACCESS (IF:3.4[JCR-2023],3.7[5-Year])
ISSN	2169-3536
卷号	7 页码:45651-45661
发表状态	已发表
DOI	10.1109/ACCESS.2019.2905879
摘要	We present a novel semantic-driven multi-view reconstruction technique for producing realistic 3D human models. Our approach borrows the fragmentation concept in Cubism style painting, where the human body is decomposed into semantically meaningful fragments for conveying space and movement. We first employ deep learning-based skeleton estimation for warping a proxy human model under the canonical pose to the target multi-view input. It also conducts 3D fragment labeling on the warped model to separate different human body parts. Finally, we utilize the normal, depth, and fragment label of the proxy model as priors in the multi-view stereo reconstruction process. The comprehensive experiments have shown that our reconstruction technique outperforms the state-of-the-art methods in robustness and accuracy, especially near occlusion boundaries and on textureless regions. In particular, it manages to significantly reduce the "adhesive" artifacts commonly observed in MVS that incorrectly stitches different body parts.
关键词	3D Reconstruction human shape semantic analysis multi-view stereo
URL	查看原文
收录类别	SCI ; SCIE ; EI
语种	英语
资助项目	SHEITC[2018-RGZN-01011]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000465620900001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号	20191806845576
EI主题词	Adhesives ; Deep learning ; Image reconstruction ; Semantics ; Textures
EI分类号	Data Processing and Image Processing:723.2
原始文献类型	Article
来源库	IEEE
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/34290
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_虞晶怡组
作者单位	1.University of Chinese Academy of Sciences, Beijing, China 2.DGene Inc., Shanghai, China 3.School of Information Science and Technology, ShanghaiTech University, Shanghai, China
推荐引用方式 GB/T 7714	Yingliang Zhang,Xi Luo,Wei Yang,et al. Fragmentation Guided Human Shape Reconstruction[J]. IEEE ACCESS,2019,7:45651-45661.
APA	Yingliang Zhang,Xi Luo,Wei Yang,&Jingyi Yu.(2019).Fragmentation Guided Human Shape Reconstruction.IEEE ACCESS,7,45651-45661.
MLA	Yingliang Zhang,et al."Fragmentation Guided Human Shape Reconstruction".IEEE ACCESS 7(2019):45651-45661.