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 2021-12-13 14:50
Latent expression separation using the locality of changes in the real image
Toshiki Hazama (Ritsumeikan Univ.), Masataka Seo (OIT), Yen-Wei Chen (Ritsumeikan Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) GAN, a deep generative model, makes a great contribution to the image generation task. However, one of the problems that is currently insufficient is that it is difficult to predict the correspondence between output and input. On the other hand, there are some types of deformation of the subject image that change locally and cannot be confirmed unless the resolution is above a certain level. From this, in this research, it is considered that the information expressing the deformation of the image is included in the information added when the resolution is increased, and the realization of highly accurate control of the generated image by providing the latent variable corresponding to the resolution. It aims to.
Keyword (in Japanese) (See Japanese page) 
(in English) Generative Adversarial Network / Disentanglement / Latent variable / / / / /  
Reference Info. ITE Tech. Rep., vol. 45, no. 39, ME2021-95, pp. 29-31, Dec. 2021.
Paper # ME2021-95 
Date of Issue 2021-12-06 (ME) 
ISSN Print edition: ISSN 1342-6893    Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee ME  
Conference Date 2021-12-13 - 2021-12-13 
Place (in Japanese) (See Japanese page) 
Place (in English) online 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To ME 
Conference Code 2021-12-ME 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Latent expression separation using the locality of changes in the real image 
Sub Title (in English)  
Keyword(1) Generative Adversarial Network  
Keyword(2) Disentanglement  
Keyword(3) Latent variable  
Keyword(4)  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Toshiki Hazama  
1st Author's Affiliation Ritsumeikan University (Ritsumeikan Univ.)
2nd Author's Name Masataka Seo  
2nd Author's Affiliation Osaka Institute of Technology (OIT)
3rd Author's Name Yen-Wei Chen  
3rd Author's Affiliation Ritsumeikan University (Ritsumeikan 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 2021-12-13 14:50:00 
Presentation Time 30 minutes 
Registration for ME 
Paper # ME2021-95 
Volume (vol) vol.45 
Number (no) no.39 
Page pp.29-31 
#Pages
Date of Issue 2021-12-06 (ME) 


[Return to Top Page]

[Return to ITE Web Page]


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