Multi-Dimensional Residual Dense Attention Network for Stereo Matching
Zhang, Guanghui1,2; Zhu, Dongchen1; Shi, Wenjun1,2; Ye, Xiaoqing1,2; Li, Jiamao1,2; Zhang, Xiaolin1,2,3
Source PublicationIEEE ACCESS
AbstractVery deep convolutional neural networks (CNNs) have recently achieved great success in stereo matching. It is still highly desirable to learn a robust feature map to improve ill-posed regions, such as weakly textured regions, reflective surfaces, and repetitive patterns. Therefore, we propose an endto-end multi-dimensional residual dense attention network (MRDA-Net) in this paper, focusing on more comprehensive pixel-wise feature extraction. Our proposed network consists of two parts: the 2D residual dense attention net for feature extraction and the 3D convolutional attention net for matching. Our designed 2D residual dense attention net uses a dense network structure to fully exploit the hierarchical features from preceding convolutional layers and uses residual network structure to fuse low-level structure information and high-level semantic information. The 2D attention module of the net aims to adaptively recalibrate channel-wise features to be more concerned about informative features. Our proposed 3D convolutional attention net further expands attention mechanism for matching. The stacked hourglass module of the net is exploited to extract multi-scale context information as well as geometry information. The novel 3D attention module of the net aggregates hierarchical sub-cost volumes adaptively instead of manually and then achieves a comprehensive recalibrated cost volume for more correct disparity computation. The experiments demonstrate that our approach achieves the state-of-the-art accuracy on Scene Flow dataset and KITTI 2012 and KITTI 2015 Stereo datasets.
KeywordStereo matching multi-dimensional residual dense attention hierarchical 3D attention mechanism
Indexed BySCI ; EI
Funding ProjectShanghai Science and Technology Committee, China[17511108202]
WOS Research AreaComputer Science ; Engineering ; Telecommunications
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS IDWOS:000466706300001
EI Accession Number20192407025701
EI KeywordsConvolution ; Deep neural networks ; Extraction ; Feature extraction ; Neural networks ; Semantics ; Textures
EI Classification NumberInformation Theory and Signal Processing:716.1 ; Data Processing and Image Processing:723.2 ; Chemical Operations:802.3
Original Document TypeArticle
Citation statistics
Cited Times:7[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Corresponding AuthorLi, Jiamao
Affiliation1.Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Bion Vis Syst Lab, State Key Lab Transducer Technol, Shanghai 200050, Peoples R China
2.Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100049, Peoples R China
3.ShanghaiTech Univ, Sch Informat & Technol, Shanghai 200050, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Guanghui,Zhu, Dongchen,Shi, Wenjun,et al. Multi-Dimensional Residual Dense Attention Network for Stereo Matching[J]. IEEE ACCESS,2019,7(99):51681-51690.
APA Zhang, Guanghui,Zhu, Dongchen,Shi, Wenjun,Ye, Xiaoqing,Li, Jiamao,&Zhang, Xiaolin.(2019).Multi-Dimensional Residual Dense Attention Network for Stereo Matching.IEEE ACCESS,7(99),51681-51690.
MLA Zhang, Guanghui,et al."Multi-Dimensional Residual Dense Attention Network for Stereo Matching".IEEE ACCESS 7.99(2019):51681-51690.
Files in This Item: Download All
File Name/Size DocType Version Access License
10.1109@ACCESS.2019.(48217KB)期刊论文未知开放获取UnknownView Download
Related Services
Usage statistics
Scholar Google
Similar articles in Scholar Google
[Zhang, Guanghui]'s Articles
[Zhu, Dongchen]'s Articles
[Shi, Wenjun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Guanghui]'s Articles
[Zhu, Dongchen]'s Articles
[Shi, Wenjun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Guanghui]'s Articles
[Zhu, Dongchen]'s Articles
[Shi, Wenjun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 10.1109@ACCESS.2019.2911618.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.