STAR-TM: STructure Aware Reconstruction of Textured Mesh From Single Image

doi:10.1109/TPAMI.2023.3305630

	STAR-TM: STructure Aware Reconstruction of Textured Mesh From Single Image
	Wu, Tong 1,2; Gao, Lin 1,2; Zhang, Ling-Xiao 1,2; Lai, Yu-Kun 3; Zhang, Hao 4
	2023-12-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	45 期号:12 页码:15680-15693
摘要	We present a novel method for single-view 3D reconstruction of textured meshes, with a focus to address the primary challenge surrounding texture inference and transfer. Our key observation is that learning textured reconstruction in a structure-aware and globally consistent manner is effective in handling the severe ill-posedness of the texturing problem and significant variations in object pose and texture details. Specifically, we perform structured mesh reconstruction, via a retrieval-and-assembly approach, to produce a set of genus-zero parts parameterized by deformable boxes and endowed with semantic information. For texturing, we first transfer visible colors from the input image onto the unified UV texture space of the deformable boxes. Then we combine a learned transformer model for per-part texture completion with a global consistency loss to optimize inter-part texture consistency. Our texture completion model operates in a VQ-VAE embedding space and is trained end-to-end, with the transformer training enhanced with retrieved texture instances to improve texture completion performance amid significant occlusion. Extensive experiments demonstrate higher-quality textured mesh reconstruction obtained by our method over state-of-the-art alternatives, both quantitatively and qualitatively, as reflected by a better recovery of texture coherence and details.
关键词	Image reconstruction Shape Transformers Periodic structures Three-dimensional displays Semantics Training Structure-aware single-view 3D reconstruction textured meshes texture completion transformer
DOI	10.1109/TPAMI.2023.3305630
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62061136007] ; Beijing Municipal Natural Science Foundation for Distinguished Young Scholars[JQ21013] ; Royal Society Newton Advanced Fellowship[NAF\R2\192151] ; Youth Innovation Promotion Association CAS
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001130146400101
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38372
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, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100045, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF10 3AT, Wales 4.Simon Fraser Univ, Sch Comp Sci, Burnaby, BC V5A 1S6, Canada
推荐引用方式 GB/T 7714	Wu, Tong,Gao, Lin,Zhang, Ling-Xiao,et al. STAR-TM: STructure Aware Reconstruction of Textured Mesh From Single Image[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(12):15680-15693.
APA	Wu, Tong,Gao, Lin,Zhang, Ling-Xiao,Lai, Yu-Kun,&Zhang, Hao.(2023).STAR-TM: STructure Aware Reconstruction of Textured Mesh From Single Image.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(12),15680-15693.
MLA	Wu, Tong,et al."STAR-TM: STructure Aware Reconstruction of Textured Mesh From Single Image".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.12(2023):15680-15693.