Feature-Preserved 3D Canonical Form

doi:10.1007/s11263-012-0548-1

CORC > 北京大学 > 信息科学技术学院

	Feature-Preserved 3D Canonical Form
	Lian, Zhouhui ; Godil, Afzal ; Xiao, Jianguo
刊名	国际计算机视觉杂志
	2013
关键词	Canonical form Multidimensional scaling 3D shape retrieval Non-rigid NONRIGID REGISTRATION MODEL RETRIEVAL RECOGNITION SURFACES DISTRIBUTIONS SIGNATURES DISTANCES
DOI	10.1007/s11263-012-0548-1
英文摘要	Measuring the dissimilarity between non-rigid objects is a challenging problem in 3D shape retrieval. One potential solution is to construct the models' 3D canonical forms (i.e., isometry-invariant representations in 3D Euclidean space) on which any rigid shape matching algorithm can be applied. However, existing methods, which are typically based on embedding procedures, result in greatly distorted canonical forms, and thus could not provide satisfactory performance to distinguish non-rigid models. In this paper, we present a feature-preserved canonical form for non-rigid 3D watertight meshes. The basic idea is to naturally deform original models against corresponding initial canonical forms calculated by Multidimensional Scaling (MDS). Specifically, objects are first segmented into near-rigid subparts, and then, through properly-designed rotations and translations, original subparts are transformed into poses that correspond well with their positions and directions on MDS canonical forms. Final results are obtained by solving nonlinear minimization problems for optimal alignments and smoothing boundaries between subparts. Experiments on two non-rigid 3D shape benchmarks not only clearly verify the advantages of our algorithm against existing approaches, but also demonstrate that, with the help of the proposed canonical form, we can obtain significantly better retrieval accuracy compared to the state of the art.; http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000315501800013&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701 ; Computer Science, Artificial Intelligence; SCI(E); EI; 4; ARTICLE; 1-3; 221-238; 102
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/161798]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Lian, Zhouhui,Godil, Afzal,Xiao, Jianguo. Feature-Preserved 3D Canonical Form[J]. 国际计算机视觉杂志,2013.
APA	Lian, Zhouhui,Godil, Afzal,&Xiao, Jianguo.(2013).Feature-Preserved 3D Canonical Form.国际计算机视觉杂志.
MLA	Lian, Zhouhui,et al."Feature-Preserved 3D Canonical Form".国际计算机视觉杂志 (2013).