Title:
METHOD AND DEVICE FOR MACHINE LEARNING-BASED IMAGE COMPRESSION USING GLOBAL CONTEXT
Document Type and Number:
WIPO Patent Application WO/2020/242260
Kind Code:
A1
Abstract:
Provided are a method and device for machine learning-based image compression using global context. A disclosed image compression network employs an existing image quality enhancement network for an end-to-end joint learning scheme. The image compression network can jointly optimize image compression and quality enhancement. Image compression networks and image enhancement networks can be easily combined within an integrated architecture that minimizes total loss, and can be easily jointed and optimized.
More Like This:
Inventors:
LEE JOO-YOUNG (KR)
CHO SEUNG-HYUN (KR)
KO HYUNSUK (KR)
KWON HYOUNG-JIN (KR)
KIM YOUN-HEE (KR)
KIM JONG-HO (KR)
JEONG SE-YOON (KR)
KIM HUI-YONG (KR)
CHOI JIN-SOO (KR)
CHO SEUNG-HYUN (KR)
KO HYUNSUK (KR)
KWON HYOUNG-JIN (KR)
KIM YOUN-HEE (KR)
KIM JONG-HO (KR)
JEONG SE-YOON (KR)
KIM HUI-YONG (KR)
CHOI JIN-SOO (KR)
Application Number:
PCT/KR2020/007039
Publication Date:
December 03, 2020
Filing Date:
May 29, 2020
Export Citation:
Assignee:
ELECTRONICS & TELECOMMUNICATIONS RES INST (KR)
International Classes:
H04N1/41; G06N20/00
Foreign References:
| US20170105005A1 | 2017-04-13 | |||
| US10225607B1 | 2019-03-05 | |||
| KR20180001428A | 2018-01-04 | |||
| CN106713935A | 2017-05-24 |
Other References:
LEE, JOOYOUNG ET AL.: "Context-adaptive Entropy Model for End-to-end Optimized Image Compression", ARXIV: 1809.10452V4, 6 May 2019 (2019-05-06), pages 1 - 20, XP081202283, Retrieved from the Internet [retrieved on 20200814]
Attorney, Agent or Firm:
HANYANG PATENT FIRM (KR)
Download PDF: