TPN: TOPOLOGICAL PERCEPTION NETWORK FOR 3D MESH REPRESENTATION

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	TPN: TOPOLOGICAL PERCEPTION NETWORK FOR 3D MESH REPRESENTATION
	Ma BT(马兵涛)1,2,3; Cong Y(丛杨)1,2; Liu HS(刘洪森)1,2,3; Tang X(唐旭)1,2
	2020
会议日期	October 25-28, 2020
会议地点	Virtual Conference
关键词	3D mesh classification and retrieval Topological attention
页码	2711-2715
英文摘要	As an important type of geometric data for 3D shapes, the unique topological connection makes the mesh more powerful than other types of data, but it also introduces complexity and irregularity. In this paper, we propose a Topological Perception Network (TPN) that consumes meshes directly to learn 3D shape representation via informative topology property. More specifically, to tackle the complexity and irregularity problem, a Topological Perception Attention (TPA) is designed that could incorporate local topological information efficiently via focusing on more important edges of the local topological neighborhood. Meanwhile, it could be stacked to produce global shape representation. Compared with the state-of-the-art, the proposed TPN uses less than half of the vertex number to get better performance, while costing less memory and computational time. Experiments on Model-Net40 and ShapeNet Core55 datasets demonstrate the effectiveness of our method on classification and retrieval.
源文献作者	The Institute of Electrical and Electronics Engineers Signal Processing Society
产权排序	1
会议录	2020 IEEE International Conference on Image Processing (ICIP 2020)
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISBN号	978-1-7281-6395-6
WOS记录号	WOS:000646178502164
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/27996]
专题	沈阳自动化研究所_机器人学研究室
通讯作者	Cong Y(丛杨)
作者单位	1.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110016 China 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China 3.University of Chinese Academy of Sciences,100049, China
推荐引用方式 GB/T 7714	Ma BT,Cong Y,Liu HS,et al. TPN: TOPOLOGICAL PERCEPTION NETWORK FOR 3D MESH REPRESENTATION[C]. 见:. Virtual Conference. October 25-28, 2020.