Institute of Computing Technology, Chinese Academy IR
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 |
ISSN | 1319-1578 |
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 |
DOI | 10.1016/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。 |
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。
修改评论