Learning local shape descriptors for computing non-rigid dense correspondence

doi:10.1007/s41095-020-0163-y

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 三维可视计算

	Learning local shape descriptors for computing non-rigid dense correspondence
	Jianwei Guo; Hanyu Wang ; Zhanglin Cheng ; Xiaopeng Zhang; Dong-Ming Yan
发表期刊	computationalvisualmedia
ISSN	2096-0433
	2020
卷号	6 期号:1 页码:95-112
摘要	A discriminative local shape descriptor plays an important role in various applications. In this paper, we present a novel deep learning framework that derives discriminative local descriptors for deformable 3D shapes. We use local “geometry images” to encode the multi-scale local features of a point, via an intrinsic parameterization method based on geodesic polar coordinates. This new parameterization provides robust geometry images even for badly-shaped triangular meshes. Then a triplet network with shared architecture and parameters is used to perform deep metric learning; its aim is to distinguish between similar and dissimilar pairs of points. Additionally, a newly designed triplet loss function is minimized for improved, accurate training of the triplet network. To solve the dense correspondence problem, an efficient sampling approach is utilized to achieve a good compromise between training performance and descriptor quality. During testing, given a geometry image of a point of interest, our network outputs a discriminative local descriptor for it. Extensive testing of non-rigid dense shape matching on a variety of benchmarks demonstrates the superiority of the proposed descriptors over the state-of-the-art alternatives.
DOI	10.1007/s41095-020-0163-y
语种	英语
七大方向——子方向分类	计算机图形学与虚拟现实
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41487
专题	多模态人工智能系统全国重点实验室_三维可视计算
作者单位	1.Institute of Automation, Chinese Academy of Sciences 2.University of Maryland-College Park 3.Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Jianwei Guo,Hanyu Wang,Zhanglin Cheng,et al. Learning local shape descriptors for computing non-rigid dense correspondence[J]. computationalvisualmedia,2020,6(1):95-112.
APA	Jianwei Guo,Hanyu Wang,Zhanglin Cheng,Xiaopeng Zhang,&Dong-Ming Yan.(2020).Learning local shape descriptors for computing non-rigid dense correspondence.computationalvisualmedia,6(1),95-112.
MLA	Jianwei Guo,et al."Learning local shape descriptors for computing non-rigid dense correspondence".computationalvisualmedia 6.1(2020):95-112.