Recent Advances in Conventional and Deep Learning-Based Depth Completion: A Survey | |
Xie, Zexiao2; Yu, Xiaoxuan2; Gao, Xiang1,2; Li, Kunqian2; Shen, Shuhan1,3,4 | |
刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
2022-09-02 | |
页码 | 21 |
关键词 | Task analysis Learning systems Noise measurement Laser radar Image color analysis Deep learning Data integration Data fusion deep learning depth completion loss function RGB-D and LiDAR data |
ISSN号 | 2162-237X |
DOI | 10.1109/TNNLS.2022.3201534 |
通讯作者 | Gao, Xiang(xgao@ouc.edu.cn) ; Shen, Shuhan(shshen@nlpr.ia.ac.cn) |
英文摘要 | Depth completion aims to recover pixelwise depth from incomplete and noisy depth measurements with or without the guidance of a reference RGB image. This task attracted considerable research interest due to its importance in various computer vision-based applications, such as scene understanding, autonomous driving, 3-D reconstruction, object detection, pose estimation, trajectory prediction, and so on. As the system input, an incomplete depth map is usually generated by projecting the 3-D points collected by ranging sensors, such as LiDAR in outdoor environments, or obtained directly from RGB-D cameras in indoor areas. However, even if a high-end LiDAR is employed, the obtained depth maps are still very sparse and noisy, especially in the regions near the object boundaries, which makes the depth completion task a challenging problem. To address this issue, a few years ago, conventional image processing-based techniques were employed to fill the holes and remove the noise from the relatively dense depth maps obtained by RGB-D cameras, while deep learning-based methods have recently become increasingly popular and inspiring results have been achieved, especially for the challenging situation of LiDAR-image-based depth completion. This article systematically reviews and summarizes the works related to the topic of depth completion in terms of input modalities, data fusion strategies, loss functions, and experimental settings, especially for the key techniques proposed in deep learning-based multiple input methods. On this basis, we conclude by presenting the current status of depth completion and discussing several prospects for its future research directions. |
资助项目 | National Science Foundation of China[62003319] ; National Science Foundation of China[42076192] ; National Science Foundation of China[62076026] ; Shandong Provincial Natural Science Foundation[ZR2020QF075] |
WOS关键词 | SINGLE IMAGE ; LIDAR DATA ; NETWORK ; FUSION ; FEATURES ; MODEL |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000852238700001 |
资助机构 | National Science Foundation of China ; Shandong Provincial Natural Science Foundation |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/50113] |
专题 | 自动化研究所_模式识别国家重点实验室_机器人视觉团队 |
通讯作者 | Gao, Xiang; Shen, Shuhan |
作者单位 | 1.Chinese Acad Sci, Inst Automat CASIA, SenseTime Res Grp, Beijing 100190, Peoples R China 2.Ocean Univ China, Coll Engn, Qingdao 266100, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Xie, Zexiao,Yu, Xiaoxuan,Gao, Xiang,et al. Recent Advances in Conventional and Deep Learning-Based Depth Completion: A Survey[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022:21. |
APA | Xie, Zexiao,Yu, Xiaoxuan,Gao, Xiang,Li, Kunqian,&Shen, Shuhan.(2022).Recent Advances in Conventional and Deep Learning-Based Depth Completion: A Survey.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,21. |
MLA | Xie, Zexiao,et al."Recent Advances in Conventional and Deep Learning-Based Depth Completion: A Survey".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022):21. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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