典型文献
Semantics-aware transformer for 3D reconstruction from binocular images
文献摘要：
Existing multi-view three-dimensional(3D)reconstruction methods can only capture single type of feature from input view,failing to obtain fine-grained semantics for reconstructing the complex shapes.They rarely explore the semantic association between input views,leading to a rough 3D shape.To address these challenges,we propose a seman-tics-aware transformer(SATF)for 3D reconstruction.It is composed of two parallel view transformer encoders and a point cloud transformer decoder,and takes two red,green and blue(RGB)images as input and outputs a dense point cloud with richer details.Each view transformer encoder can learn a multi-level feature,facilitating characterizing fine-grained semantics from input view.The point cloud transformer decoder explores a semantically-associated fea-ture by aligning the semantics of two input views,which describes the semantic association between views.Further-more,it can generate a sparse point cloud using the semantically-associated feature.At last,the decoder enriches the sparse point cloud for producing a dense point cloud with richer details.Extensive experiments on the ShapeNet data-set show that our SATF outperforms the state-of-the-art methods.
文献关键词：
中图分类号：
作者姓名：
JIA Xin;YANG Shourui;GUAN Diyi
作者机构：
The Engineering Research Center of Learning-Based Intelligent System and the Key Laboratory of Computer Vision and System of Ministry of Education,Tianjin University of Technology,Tianjin 300384,China;Zhejiang University of Technology,Hangzhou 310014,China
文献出处：
引用格式：
[1]JIA Xin;YANG Shourui;GUAN Diyi-.Semantics-aware transformer for 3D reconstruction from binocular images)[J].光电子快报（英文版）,2022(05):293-299
A类：
seman,SATF
B类：
Semantics,aware,transformer,reconstruction,from,binocular,images,Existing,multi,three,dimensional,methods,can,only,capture,single,type,feature,input,failing,obtain,fine,grained,semantics,reconstructing,complex,shapes,They,rarely,association,between,views,leading,rough,To,address,these,challenges,propose,It,composed,two,parallel,encoders,point,cloud,decoder,takes,red,green,blue,RGB,outputs,dense,richer,details,Each,learn,level,facilitating,characterizing,explores,semantically,associated,by,aligning,which,describes,Further,more,generate,sparse,using,At,last,enriches,producing,Extensive,experiments,ShapeNet,data,set,show,that,our,outperforms,state,art
AB值：
0.506798
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
