CSpace  > 中国科学院计算技术研究所期刊论文  > 英文
Structure recovery from single omnidirectional image with distortion-aware learning
Meng, Ming1; Zhou, Yi2; Zuo, Dongshi3; Li, Zhaoxin4; Zhou, Zhong5
2024-09-01
发表期刊JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
ISSN1319-1578
卷号36期号:7页码:14
摘要Recovering structures from images with 180(degrees) or 360(degrees) FoV is pivotal in computer vision and computational photography, particularly for VR/AR/MR and autonomous robotics applications. Due to varying distortions and the complexity of indoor scenes, recovering flexible structures from a single image is challenging. We introduce OmniSRNet, a comprehensive deep learning framework that merges distortion-aware learning with bidirectional LSTM. Utilizing a curated dataset with optimized panorama and expanded fisheye images, our framework features a distortion-aware module (DAM) for extracting features and a horizontal and vertical step module (HVSM) of LSTM for contextual predictions. OmniSRNet excels in applications such as VR-based house viewing and MR-based video surveillance, achieving leading results on cuboid and non-cuboid datasets. The code and dataset can be accessed at https://github.com/mmlph/OmniSRNet/.
关键词Structure recovery Omnidirectional dataset DAM HVSM
DOI10.1016/j.jksuci.2024.102151
收录类别SCI
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Information Systems
WOS记录号WOS:001312948500001
出版者ELSEVIER
引用统计
文献类型期刊论文
条目标识符http://119.78.100.204/handle/2XEOYT63/39598
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Meng, Ming
作者单位1.Commun Univ China, Sch Data Sci & Media Intelligence, Beijing, Peoples R China
2.Beijing BigView Technol Co Ltd, Beijing, Peoples R China
3.Inner Mongolia Agr Univ, Coll Comp & Informat Engn, Hohhot, Peoples R China
4.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
5.Beihang Univ, State Key Lab Virtual Real Technol & Syst, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Meng, Ming,Zhou, Yi,Zuo, Dongshi,et al. Structure recovery from single omnidirectional image with distortion-aware learning[J]. JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES,2024,36(7):14.
APA Meng, Ming,Zhou, Yi,Zuo, Dongshi,Li, Zhaoxin,&Zhou, Zhong.(2024).Structure recovery from single omnidirectional image with distortion-aware learning.JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES,36(7),14.
MLA Meng, Ming,et al."Structure recovery from single omnidirectional image with distortion-aware learning".JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 36.7(2024):14.
条目包含的文件
条目无相关文件。
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
[Meng, Ming]的文章
[Zhou, Yi]的文章
[Zuo, Dongshi]的文章
百度学术
百度学术中相似的文章
[Meng, Ming]的文章
[Zhou, Yi]的文章
[Zuo, Dongshi]的文章
必应学术
必应学术中相似的文章
[Meng, Ming]的文章
[Zhou, Yi]的文章
[Zuo, Dongshi]的文章
相关权益政策
暂无数据
收藏/分享
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。