CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Learning stratified 3D reconstruction
Dong, Qiulei1,3,4; Shu, Mao1; Cui, Hainan1; Xu, Huarong1,2; Hu, Zhanyi1,3,4
2018-02-01
发表期刊SCIENCE CHINA-INFORMATION SCIENCES
卷号61期号:2页码:1-16
文章类型Article
摘要Stratified 3D reconstruction, or a layer-by-layer 3D reconstruction upgraded from projective to affine, then to the final metric reconstruction, is a well-known 3D reconstruction method in computer vision. It is also a key supporting technology for various well-known applications, such as streetview, smart3D, oblique photogrammetry. Generally speaking, the existing computer vision methods in the literature can be roughly classified into either the geometry-based approaches for spatial vision or the learning-based approaches for object vision. Although deep learning has demonstrated tremendous success in object vision in recent years, learning 3D scene reconstruction from multiple images is still rare, even not existent, except for those on depth learning from single images. This study is to explore the feasibility of learning the stratified 3D reconstruction from putative point correspondences across images, and to assess whether it could also be as robust to matching outliers as the traditional geometry-based methods do. In this study, a special parsimonious neural network is designed for the learning. Our results show that it is indeed possible to learn a stratified 3D reconstruction from noisy image point correspondences, and the learnt reconstruction results appear satisfactory although they are still not on a par with the state-of-the-arts in the structure-from-motion community due to largely its lack of an explicit robust outlier detector such as random sample consensus (RANSAC). To the best of our knowledge, our study is the first attempt in the literature to learn 3D scene reconstruction from multiple images. Our results also show that how to implicitly or explicitly integrate an outlier detector in learning methods is a key problem to solve in order to learn comparable 3D scene structures to those by the current geometry-based state-of-the-arts. Otherwise any significant advancement of learning 3D structures from multiple images seems difficult, if not impossible. Besides, we even speculate that deep learning might be, in nature, not suitable for learning 3D structure from multiple images, or more generally, for solving spatial vision problems.
关键词Stratified 3d Reconstruction Learning Deep Neural Networks Outlier Detector Spatial Vision
WOS标题词Science & Technology ; Technology
DOI10.1007/s11432-017-9234-7
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China(61333015 ; 61375042 ; 61421004 ; 61573359 ; 61772444)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号WOS:000423635200003
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/21946
专题模式识别国家重点实验室_机器人视觉
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Xiamen Inst Technol, Dept Comp Sci & Technol, Xiamen 361024, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714
Dong, Qiulei,Shu, Mao,Cui, Hainan,et al. Learning stratified 3D reconstruction[J]. SCIENCE CHINA-INFORMATION SCIENCES,2018,61(2):1-16.
APA Dong, Qiulei,Shu, Mao,Cui, Hainan,Xu, Huarong,&Hu, Zhanyi.(2018).Learning stratified 3D reconstruction.SCIENCE CHINA-INFORMATION SCIENCES,61(2),1-16.
MLA Dong, Qiulei,et al."Learning stratified 3D reconstruction".SCIENCE CHINA-INFORMATION SCIENCES 61.2(2018):1-16.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Dong2017_Article_Lea(3578KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Dong, Qiulei]的文章
[Shu, Mao]的文章
[Cui, Hainan]的文章
百度学术
百度学术中相似的文章
[Dong, Qiulei]的文章
[Shu, Mao]的文章
[Cui, Hainan]的文章
必应学术
必应学术中相似的文章
[Dong, Qiulei]的文章
[Shu, Mao]的文章
[Cui, Hainan]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Dong2017_Article_LearningStratified3DReconstruc.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。