Information: Join today and make your research activities more affordable! Technical workshop participation fees and annual registration fees are available at member rates.
Notice: [Important] Announcement of Changes to Registration Fee Payment and Manuscript Upload Procedures for IEICE Technical Meetings[Type 1 Only]
IEICE Technical Committee Submission System
Conference Paper's Information		 Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation
A Fast Gaussian Mixture Entropy Model for Learned Image Compression
Shimon Murai (Waseda Univ.), Fangzheng Lin (Science Tokyo), Jiro Katto (Waseda Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) Learned image compression models transform the input image into bit stream through probability modeling and entropy coding. While most of the models assume Gaussian distribution for the latent representations, it is known that the use of Gaussian mixture distribution results in superior performance. However, existing Gaussian mixture methods demand high computational cost. We tackled this issue by installing new algorithms that skip table construction, numerical approximation and CPU parallelization, to achieve ~90x acceleration while slightly improving its performance.
Keyword (in Japanese) (See Japanese page) 
(in English) Image Compression / Deep Learning / Entropy Coding / Image Coding / Gaussian Mixture Model / / /  
Reference Info. IEICE Tech. Rep.
Paper #  
Date of Issue  
ISSN  
Download PDF

Conference Information
Committee PCSJ-IMPS IE SIP ITE-ME  
Conference Date 2025-11-17 - 2025-11-19 
Place (in Japanese) (See Japanese page) 
Place (in English) Gotembakogen Hotel 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Picture Coding Symposium of Japan and Image Media Processing Symposium 
Paper Information
Registration To PCSJ-IMPS 
Conference Code 2025-11-PCSJ-IMPS-IE-SIP-ME 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) A Fast Gaussian Mixture Entropy Model for Learned Image Compression 
Sub Title (in English)  
Keyword(1) Image Compression  
Keyword(2) Deep Learning  
Keyword(3) Entropy Coding  
Keyword(4) Image Coding  
Keyword(5) Gaussian Mixture Model  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Shimon Murai  
1st Author's Affiliation Waseda University (Waseda Univ.)
2nd Author's Name Fangzheng Lin  
2nd Author's Affiliation Institute of Science Tokyo (Science Tokyo)
3rd Author's Name Jiro Katto  
3rd Author's Affiliation Waseda University (Waseda 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 ()
21st Author's Name  
21st Author's Affiliation ()
22nd Author's Name  
22nd Author's Affiliation ()
23rd Author's Name  
23rd Author's Affiliation ()
24th Author's Name  
24th Author's Affiliation ()
25th Author's Name  
25th Author's Affiliation ()
26th Author's Name / /
26th Author's Affiliation ()
()
27th Author's Name / /
27th Author's Affiliation ()
()
28th Author's Name / /
28th Author's Affiliation ()
()
29th Author's Name / /
29th Author's Affiliation ()
()
30th Author's Name / /
30th Author's Affiliation ()
()
31st Author's Name / /
31st Author's Affiliation ()
()
32nd Author's Name / /
32nd Author's Affiliation ()
()
33rd Author's Name / /
33rd Author's Affiliation ()
()
34th Author's Name / /
34th Author's Affiliation ()
()
35th Author's Name / /
35th Author's Affiliation ()
()
36th Author's Name / /
36th Author's Affiliation ()
()
Speaker Author-1 
Date Time  
Presentation Time minutes 
Registration for PCSJ-IMPS 
Paper #  
Volume (vol) vol. 
Number (no)  
Page  
#Pages  
Date of Issue  

[Return to Top Page]

[Return to IEICE Web Page]

(Line Height for English Pages: 1)
The Institute of Electronics, Information and Communication Engineers (IEICE), Japan