中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
STAR-TM: STructure Aware Reconstruction of Textured Mesh From Single Image

文献类型：期刊论文

作者Wu, Tong3,4; Gao, Lin3,4; Zhang, Ling-Xiao3,4; Lai, Yu-Kun2; Zhang, Hao1
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2023-12-01
卷号45期号:12页码:15680-15693
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
ISSN号0162-8828
DOI10.1109/TPAMI.2023.3305630
英文摘要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.
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
语种英语
WOS记录号WOS:001130146400101
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/38371]  
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.Simon Fraser Univ, Sch Comp Sci, Burnaby, BC V5A 1S6, Canada
2.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF10 3AT, Wales
3.Univ Chinese Acad Sci, Beijing 101408, Peoples R China
4.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100045, Peoples R China
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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

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。