ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2019-12-20 14:55
Depth from Focal Stack by Deep Neural Network
Chen Baihui, Takahashi Keita, Fujii Toshiaki (Nagoya Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) Light field theory is a heated topic in computer vision. Focal stack is one of the one of the most significant characteristics of light field. However, in most learning methods, less attention was paid on focal stack. Therefore, we put forward depth estimation of light field image by machine learning method using focal stack. We extract depth information and performed by depth map. In experiment, we use deep neural network and a complete dataset for training, and then make some evaluations.
Keyword (in Japanese) (See Japanese page) 
(in English) light field / focal stack / depth estimation / neural network / / / /  
Reference Info. ITE Tech. Rep., vol. 43, Dec. 2019.
Paper #  
Date of Issue 2019-12-13 (IST, IDY, 3DIT) 
ISSN Print edition: ISSN 1342-6893    Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee 3DMT IDY IST  
Conference Date 2019-12-20 - 2019-12-20 
Place (in Japanese) (See Japanese page) 
Place (in English) NHK Nagoya Station 
Topics (in Japanese) (See Japanese page) 
Topics (in English) 3D Imaging, Hyper-Realistic Imaging, etc. 
Paper Information
Registration To 3DMT 
Conference Code 2019-12-3DIT-IDY-IST 
Language English (Japanese title is available) 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Depth from Focal Stack by Deep Neural Network 
Sub Title (in English)  
Keyword(1) light field  
Keyword(2) focal stack  
Keyword(3) depth estimation  
Keyword(4) neural network  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Chen Baihui  
1st Author's Affiliation Nagoya University (Nagoya Univ.)
2nd Author's Name Takahashi Keita  
2nd Author's Affiliation Nagoya University (Nagoya Univ.)
3rd Author's Name Fujii Toshiaki  
3rd Author's Affiliation Nagoya University (Nagoya Univ.)
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2019-12-20 14:55:00 
Presentation Time 25 minutes 
Registration for 3DMT 
Paper # IST2019-62, IDY2019-62, 3DIT2019-37 
Volume (vol) vol.43 
Number (no) no.43 
Page pp.17-19 
#Pages
Date of Issue 2019-12-13 (IST, IDY, 3DIT) 


[Return to Top Page]

[Return to ITE Web Page]


The Institute of Image Information and Television Engineers (ITE), Japan