Multi-Scale Dense Attention Network for Stereo Matching

Multi-Scale Dense Attention Network for Stereo Matching

To improve the accuracy of stereo matching, the multi-scale dense attention network (MDA-Net) is proposed. The network introduces two novel modules in the feature extraction stage to achieve better exploit of context information: dual-path upsampling (DU) block and attention-guided context-aware pyr...

Full description

Bibliographic Details
Main Authors: Yuhui Chang, Jiangtao Xu, Zhiyuan Gao
Format: Article
Language:English
Published: MDPI AG 2020-11-01
Series:Electronics
Subjects:
stereo matching
deep learning
attention mechanism
Online Access:https://www.mdpi.com/2079-9292/9/11/1881

Internet

https://www.mdpi.com/2079-9292/9/11/1881

Similar Items