Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
MGCN: Descriptor Learning using Multiscale GCNs | |
Wang, Yiqun1,2,3; Ren, Jing3; Yan, Dong-Ming1,2; Guo, Jianwei1,2; Zhang, Xiaopeng1,2; Wonka, Peter3 | |
发表期刊 | ACM TRANSACTIONS ON GRAPHICS |
ISSN | 0730-0301 |
2020-07-01 | |
卷号 | 39期号:4页码:15 |
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. |
关键词 | Multiscale Energy Decomposition Wavelet Convolution Shape Matching |
DOI | 10.1145/3386569.3392443 |
收录类别 | SCI |
语种 | 英语 |
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] |
项目资助者 | 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 |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Software Engineering |
WOS记录号 | WOS:000583700300095 |
出版者 | ASSOC COMPUTING MACHINERY |
七大方向——子方向分类 | 计算机图形学与虚拟现实 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/41656 |
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.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch AI, Beijing, Peoples R China 3.KAUST, Thuwal, Saudi Arabia |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
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. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
5.mgcn.pdf(32624KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论