SDM-NET: Deep Generative Network for Structured Deformable Mesh

doi:10.1145/3355089.3356488

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	SDM-NET: Deep Generative Network for Structured Deformable Mesh
	Gao, Lin 1,6; Yang, Jie 1,2,6; Wu, Tong 1,2,6; Yuan, Yu-Jie 1,2,6; Fu, Hongbo 3; Lai, Yu-Kun 4; Zhang, Hao 5
刊名	ACM TRANSACTIONS ON GRAPHICS
	2019-11-01
卷号	38 期号:6 页码:15
关键词	Shape representation variational autoencoder structure geometric details generation
ISSN号	0730-0301
DOI	10.1145/3355089.3356488
英文摘要	We introduce SDM-NET, a deep generative neural network which produces structured deformable meshes. Specifically, the network is trained to generate a spatial arrangement of closed, deformable mesh parts, which respects the global part structure of a shape collection, e.g., chairs, airplanes, etc. Our key observation is that while the overall structure of a 3D shape can be complex, the shape can usually be decomposed into a set of parts, each homeomorphic to a box, and the finer-scale geometry of the part can be recovered by deforming the box. The architecture of SDM-NET is that of a two-level variational autoencoder (VAE). At the part level, a PartVAE learns a deformable model of part geometries. At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring the coherence between global shape structure and surface details. Through extensive experiments and comparisons with the state-of-the-art deep generative models of shapes, we demonstrate the superiority of SDM-NET in generating meshes with visual quality, flexible topology, and meaningful structures, benefiting shape interpolation and other subsequent modeling tasks.
资助项目	National Natural Science Foundation of China[61828204] ; National Natural Science Foundation of China[61872440] ; Beijing Municipal Natural Science Foundation[L182016] ; Youth Innovation Promotion Association CAS ; CCF-Tencent Open Fund ; Research Grants Council of the Hong Kong Special Administrative Region, China[CityU 11237116] ; Research Grants Council of the Hong Kong Special Administrative Region, China[CityU 11300615] ; Centre for Applied Computing and Interactive Media (ACIM) of School of Creative Media, CityU ; Sense Time Research Fund
WOS研究方向	Computer Science
语种	英语
出版者	ASSOC COMPUTING MACHINERY
WOS记录号	WOS:000498397300091
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/14938]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Gao, Lin
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.City Univ Hong Kong, Sch Creat Media, Hong Kong, Peoples R China 4.Cardiff Univ, Sch Comp Sci & Informat, Cardiff, S Glam, Wales 5.Simon Fraser Univ, Sch Comp Sci, Burnaby, BC, Canada 6.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Gao, Lin,Yang, Jie,Wu, Tong,et al. SDM-NET: Deep Generative Network for Structured Deformable Mesh[J]. ACM TRANSACTIONS ON GRAPHICS,2019,38(6):15.
APA	Gao, Lin.,Yang, Jie.,Wu, Tong.,Yuan, Yu-Jie.,Fu, Hongbo.,...&Zhang, Hao.(2019).SDM-NET: Deep Generative Network for Structured Deformable Mesh.ACM TRANSACTIONS ON GRAPHICS,38(6),15.
MLA	Gao, Lin,et al."SDM-NET: Deep Generative Network for Structured Deformable Mesh".ACM TRANSACTIONS ON GRAPHICS 38.6(2019):15.