NET: Deep Generative Networks for Textured Meshes

doi:10.1145/3478513.3480503

	NET: Deep Generative Networks for Textured Meshes
	Gao, Lin 1,2; Wu, Tong 1,2; Yu-Jie Yuan 1,2; Ming-Xian Lin 1,2; Yu-Kun Lai 3; Zhang, Hao 4
	2021-12-01
发表期刊	ACM TRANSACTIONS ON GRAPHICS
ISSN	0730-0301
卷号	40 期号:6 页码:15
摘要	We introduce TM-NET, a novel deep generative model for synthesizing textured meshes in a part-aware manner. Once trained, the network can generate novel textured meshes from scratch or predict textures for a given 3D mesh, without image guidance. Plausible and diverse textures can be generated for the same mesh part, while texture compatibility between parts in the same shape is achieved via conditional generation. Specifically, our method produces texture maps for individual shape parts, each as a deformable box, leading to a natural UV map with limited distortion. The network separately embeds part geometry (via a PartVAE) and part texture (via a TextureVAE) into their respective latent spaces, so as to facilitate learning texture probability distributions conditioned on geometry. We introduce a conditional autoregressive model for texture generation, which can be conditioned on both part geometry and textures already generated for other parts to achieve texture compatibility. To produce high-frequency texture details, our TextureVAE operates in a high-dimensional latent space via dictionary-based vector quantization. We also exploit transparencies in the texture as an effective means to model complex shape structures including topological details. Extensive experiments demonstrate the plausibility, quality, and diversity of the textures and geometries generated by our network, while avoiding inconsistency issues that are common to novel view synthesis methods.
关键词	Mesh representation Mesh texture Shape generation
DOI	10.1145/3478513.3480503
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62061136007] ; National Natural Science Foundation of China[61872440] ; Royal Society Newton Advanced Fellowship ; NAF[\R2\192151] ; Youth Innovation Promotion Association CAS
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:000729846700068
出版者	ASSOC COMPUTING MACHINERY
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/18356
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 Key Lab Mobile Comp & Pervas Device, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Cardiff Univ, Sch Comp Sci & Informat, Cardiff, Wales 4.Simon Fraser Univ, Sch Comp Sci, Burnaby, BC, Canada
推荐引用方式 GB/T 7714	Gao, Lin,Wu, Tong,Yu-Jie Yuan,et al. NET: Deep Generative Networks for Textured Meshes[J]. ACM TRANSACTIONS ON GRAPHICS,2021,40(6):15.
APA	Gao, Lin,Wu, Tong,Yu-Jie Yuan,Ming-Xian Lin,Yu-Kun Lai,&Zhang, Hao.(2021).NET: Deep Generative Networks for Textured Meshes.ACM TRANSACTIONS ON GRAPHICS,40(6),15.
MLA	Gao, Lin,et al."NET: Deep Generative Networks for Textured Meshes".ACM TRANSACTIONS ON GRAPHICS 40.6(2021):15.