Relative Pose Estimation for RGB-D Human Input Scans via Implicit Function Reconstruction

doi:10.1155/2022/4351951

	Relative Pose Estimation for RGB-D Human Input Scans via Implicit Function Reconstruction
	Liu, Pengpeng 1,4; Yu, Tao 3,5; Zeng, Zhi 1; Liu, Yebin 3,5; Zhang, Guixuan 1; Song, Zhen 2
刊名	WIRELESS COMMUNICATIONS & MOBILE COMPUTING
	2022-02-11
卷号	2022 页码:9
ISSN号	1530-8669
DOI	10.1155/2022/4351951
通讯作者	Song, Zhen(songzhen@zhongxi.cn)
英文摘要	To achieve a promising performance on relative pose estimation for RGB-D scans, a considerable overlap between two RGB-D inputs is often required for most existing methods. However, in many practical applications for human scans, we often have to estimate the relative poses under arbitrary overlaps, which is challenging for existing methods. To deal with this problem, this paper presents a novel end-to-end and coarse-to-fine optimization method. Our method is self-supervision which firstly combines implicit function reconstruction with differentiable render for RGB-D human input scans at arbitrary overlaps in relative pose estimation. The insight is to take advantage of the underlying human geometry prior as much as possible. First of all, for stable coarse poses, we utilize the implicit function reconstruction to dig out abundant hidden cues from unseen regions in the initialization module. To further refine the poses, the differentiable render is leveraged to establish a self-supervision mechanism in the optimization module, which is independent of standard pipelines for feature extracting and accurate correspondence matching. More importantly, our proposed method is flexible to be extended to multiview input scans. The results and evaluations demonstrate that our optimization module is robust for real-world noisy inputs, and our approach outperforms considerably than standard pipelines in non-overlapping setups.
资助项目	Beijing Outstanding Young Scientist Program[BJJWZYJH01201910048035] ; Fundamental Research Funds for the Central Universities[YNZDA1805]
WOS关键词	REGISTRATION
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
出版者	WILEY-HINDAWI
WOS记录号	WOS:000766931800002
资助机构	Beijing Outstanding Young Scientist Program ; Fundamental Research Funds for the Central Universities
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48005]
专题	中国科学院自动化研究所
通讯作者	Song, Zhen
作者单位	1.Chinese Acad Sci CASIA, Inst Automat, Beijing, Peoples R China 2.Cent Acad Drama, Adv Res Ctr Digitalizat Tradit Drama, Beijing, Peoples R China 3.Tsinghua Univ, BNRist, Beijing, Peoples R China 4.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing, Peoples R China 5.Tsinghua Univ, Dept Automat, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Liu, Pengpeng,Yu, Tao,Zeng, Zhi,et al. Relative Pose Estimation for RGB-D Human Input Scans via Implicit Function Reconstruction[J]. WIRELESS COMMUNICATIONS & MOBILE COMPUTING,2022,2022:9.
APA	Liu, Pengpeng,Yu, Tao,Zeng, Zhi,Liu, Yebin,Zhang, Guixuan,&Song, Zhen.(2022).Relative Pose Estimation for RGB-D Human Input Scans via Implicit Function Reconstruction.WIRELESS COMMUNICATIONS & MOBILE COMPUTING,2022,9.
MLA	Liu, Pengpeng,et al."Relative Pose Estimation for RGB-D Human Input Scans via Implicit Function Reconstruction".WIRELESS COMMUNICATIONS & MOBILE COMPUTING 2022(2022):9.