Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
APPARATUS AND METHOD FOR PERFORMING ARTIFICIAL INTELLIGENCE ENCODING AND ARTIFICIAL INTELLIGENCE DECODING ON IMAGE
Document Type and Number:
WIPO Patent Application WO/2020/246756
Kind Code:
A1
Abstract:
Provided are methods and apparatus related to Artificial Intelligence (AI) downscaling and upscaling and techniques related to reducing artifact problems. Some embodiments include down-scaling an original image through a Deep Neural Network (DNN); generating, from the original image and based on frequency transform coefficients, artifact information representing a region in the first image including an artifact in the first image. Post-processing may be performed based on the artifact information to change pixels in the first image, thus reducing the effect of artifacts.

Inventors:
YANG HEECHUL (KR)
LEE JONGSEOK (KR)
PARK YOUNGO (KR)
CHOI KWANGPYO (KR)
Application Number:
PCT/KR2020/007048
Publication Date:
December 10, 2020
Filing Date:
May 29, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
H04N19/85; G06N3/08; H04N19/176; H04N19/18; H04N19/423; H04N19/82
Domestic Patent References:
WO2019009490A12019-01-10
Foreign References:
US20120177301A12012-07-12
US20140369613A12014-12-18
US20020146072A12002-10-10
US20190166379A12019-05-30
EP3567857A12019-11-13
US5850294A1998-12-15
US6748113B12004-06-08
Other References:
YUE LI ET AL.: "Learning a Convolutional Neural Network for Image Compact-Resolution", IEEE TRANSACTIONS ON IMAGE PROCESSING, vol. 28, no. 3, March 2019 (2019-03-01), pages 1092 - 1107, XP011703593, DOI: 10.1109/TIP.2018.2872876
See also references of EP 3954127A4
Attorney, Agent or Firm:
Y.P.LEE, MOCK & PARTNERS (KR)
Download PDF:



 
Previous Patent: CIRCUIT BOARD

Next Patent: SIZE-ADJUSTABLE APRON