Open AccessUnsupervised stereo image depth estimation of midan recovery structure
Author(s) -
lixianwei,
leidian
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1693/1/012144
Subject(s) - artificial intelligence , representation (politics) , consistency (knowledge bases) , estimation , computer science , computer vision , image (mathematics) , pixel , mode (computer interface) , grid , pattern recognition (psychology) , mathematics , engineering , geometry , systems engineering , politics , political science , law , operating system
The stereo image depth estimation is an important fileld in computer vision. At present, most of the researches on depth estimation based on deep learning make use of the mathematical characteristics of the image, such as left-right consistency and pixel distribution characteristics. In this paper, we pay attention to the relationship between the grid representation, which is a distance representation mode of biological system, and the depth representation. Inspired by the concept of Fourier decomposition, we propose a median recovery network structure. The Experiment shows that this network structure has a certain effect on depth estimation.