中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 三维可视计算
MGCN: Descriptor Learning using Multiscale GCNs

文献类型：期刊论文

作者Wang, Yiqun1,2,3; Ren, Jing3; Yan, Dong-Ming1,2; Guo, Jianwei1,2; Zhang, Xiaopeng1,2; Wonka, Peter3
刊名ACM TRANSACTIONS ON GRAPHICS
出版日期2020-07-01
卷号39期号:4页码:15
关键词Multiscale Energy Decomposition Wavelet Convolution Shape Matching
ISSN号0730-0301
DOI10.1145/3386569.3392443
通讯作者Wang, Yiqun(yiqun.wang@nlpr.ia.ac.cn)
英文摘要We propose a novel framework for computing descriptors for characterizing points on three-dimensional surfaces. First, we present a new non-learned feature that uses graph wavelets to decompose the Dirichlet energy on a surface. We call this new feature Wavelet Energy Decomposition Signature (WEDS). Second, we propose a new Multiscale Graph Convolutional Network (MGCN) to transform a non-learned feature to a more discriminative descriptor. Our results show that the new descriptor WEDS is more discriminative than the current state-of-the-art non-learned descriptors and that the combination of WEDS and MGCN is better than the state-of-the-art learned descriptors. An important design criterion for our descriptor is the robustness to different surface discretizations including triangulations with varying numbers of vertices. Our results demonstrate that previous graph convolutional networks significantly overlit to a particular resolution or even a particular triangulation, but MGCN generalizes well to different surface discretizations. In addition, MGCN is compatible with previous descriptors and it can also be used to improve the performance of other descriptors, such as the heat kernel signature, the wave kernel signature, or the local point signature.
资助项目National Key R&D Program of China[2018YFB2100602] ; National Key R&D Program of China[2019YFB2204104] ; National Natural Science Foundation of China[61620106003] ; National Natural Science Foundation of China[61772523] ; National Natural Science Foundation of China[61802406] ; National Natural Science Foundation of China[61972459] ; Beijing Natural Science Foundation[L182059] ; CCF-Tencent Open Research Fund ; Shenzhen Basic Research Program[JCYJ20180507182222355] ; Alibaba Group through Alibaba Innovative Research Program ; KAUST OSR Award[CRG-2017-3426]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000583700300095
出版者ASSOC COMPUTING MACHINERY
资助机构National Key R&D Program of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; CCF-Tencent Open Research Fund ; Shenzhen Basic Research Program ; Alibaba Group through Alibaba Innovative Research Program ; KAUST OSR Award
源URL[http://ir.ia.ac.cn/handle/173211/41655]  
专题模式识别国家重点实验室_三维可视计算
通讯作者Wang, Yiqun
作者单位1.Univ Chinese Acad Sci, Sch AI, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
3.KAUST, Thuwal, Saudi Arabia
推荐引用方式
GB/T 7714		 Wang, Yiqun,Ren, Jing,Yan, Dong-Ming,et al. MGCN: Descriptor Learning using Multiscale GCNs[J]. ACM TRANSACTIONS ON GRAPHICS,2020,39(4):15.
APA Wang, Yiqun,Ren, Jing,Yan, Dong-Ming,Guo, Jianwei,Zhang, Xiaopeng,&Wonka, Peter.(2020).MGCN: Descriptor Learning using Multiscale GCNs.ACM TRANSACTIONS ON GRAPHICS,39(4),15.
MLA Wang, Yiqun,et al."MGCN: Descriptor Learning using Multiscale GCNs".ACM TRANSACTIONS ON GRAPHICS 39.4(2020):15.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。