Knowledge Commons of Institute of Automation,CAS
Object Reconstruction Based on Attentive Recurrent Network from Single and Multiple Images | |
Gao, Zishu1,2![]() ![]() ![]() ![]() ![]() | |
发表期刊 | NEURAL PROCESSING LETTERS
![]() |
ISSN | 1370-4621 |
2021-01-05 | |
期号 | 53页码:18 |
摘要 | The application of traditional 3D reconstruction methods such as structure-from-motion and simultaneous localization and mapping are typically limited by illumination conditions, surface textures, and wide baseline viewpoints in the field of robotics. To solve this problem, many researchers have applied learning-based methods with convolutional neural network architectures. However, simply utilizing convolutional neural networks without taking other measures into account is computationally intensive, and the results are not satisfying. In this study, to obtain the most informative images for reconstruction, we introduce a residual block to a 2D encoder for improved feature extraction, and propose an attentive latent unit that makes it possible to select the most informative image being fed into the network rather than choosing one at random. The recurrent visual attentive network is injected into the auto-encoder network using reinforcement learning. The recurrent visual attentive network pays more attention to useful images, and the agent will quickly predict the 3D volume. This model is evaluated based on both single- and multi-view reconstructions. The experiment results show that the recurrent visual attentive network increases prediction performance in a way that is superior to other alternative methods, and our model has desirable capacity for generalization. |
关键词 | Object reconstruction Convolutional LSTM Visual attention Robotic application |
DOI | 10.1007/s11063-020-10399-1 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61873267] ; National Natural Science Foundation of China[U1713224] |
项目资助者 | National Natural Science Foundation of China |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000605149700003 |
出版者 | SPRINGER |
七大方向——子方向分类 | 多模态智能 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/42536 |
专题 | 复杂系统认知与决策实验室_先进机器人 |
通讯作者 | Li, En |
作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Hunan Univ, Coll Elect & Informat Engn, Changsha 410082, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Gao, Zishu,Li, En,Wang, Zhe,et al. Object Reconstruction Based on Attentive Recurrent Network from Single and Multiple Images[J]. NEURAL PROCESSING LETTERS,2021(53):18. |
APA | Gao, Zishu.,Li, En.,Wang, Zhe.,Yang, Guodong.,Lu, Jiwu.,...&Liang, Zize.(2021).Object Reconstruction Based on Attentive Recurrent Network from Single and Multiple Images.NEURAL PROCESSING LETTERS(53),18. |
MLA | Gao, Zishu,et al."Object Reconstruction Based on Attentive Recurrent Network from Single and Multiple Images".NEURAL PROCESSING LETTERS .53(2021):18. |
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 | ||
Gao2021_Article_Obje(1338KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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