Efficient Stereo Matching Leveraging Deep Local and Context Information

Efficient Stereo Matching Leveraging Deep Local and Context Information

Stereo matching is a challenging problem with respect to weak texture, discontinuities, illumination difference and occlusions. Therefore, a deep learning framework is presented in this paper, which focuses on the first and last stage of typical stereo methods: the matching cost computation and the...

Full description

Bibliographic Details
Main Authors: Xiaoqing Ye, Jiamao Li, Han Wang, Hexiao Huang, Xiaolin Zhang
Format: Article
Language:English
Published: IEEE 2017-01-01
Series:IEEE Access
Subjects:
Stereo vision
matching cost
disparity refinement
convolutional neural network
occlusion restoration
Online Access:https://ieeexplore.ieee.org/document/8047938/

Similar Items

Similar Items