IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD THEREOF

WIPO Patent Application WO/2020/226317

A1

An image processing apparatus obtains a first output image by applying an image to a first training network model, obtains a second output image by applying the image to a second training network model, and obtains a reconstructed image based on the first output image and the second output image. The first training network model is a model that uses a fixed parameter obtained through training of a plurality of sample images, the second training network model is trained to minimize a difference between a target image corresponding to the image and the reconstructed image.

LEE HYUNSEUNG (KR)
KIM MUN CHURL (KR)
KIM YONGWOO (KR)
CHOI JAE SEOK (KR)
MOON YOUNGSU (KR)
LEE CHEON (KR)

PCT/KR2020/005551

November 12, 2020

April 28, 2020

Click for automatic bibliography generation  

SAMSUNG ELECTRONICS CO LTD (KR)
KOREA ADVANCED INST SCI & TECH (KR)

G06T5/00; G06T3/40; G06T5/50; G06T7/13; G06T7/40

KR20180119753A	2018-11-05
US20180293707A1	2018-10-11
US20160379352A1	2016-12-29
KR101922964B1	2018-11-28
KR20190016539A	2019-02-18

YAMANAKA ET AL.: "ARXIV.org", 2017, CORNELL UNIVERSITY LIBRARY, article "Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network", pages: 14853
WANG ET AL.: "End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks", IEEE ACCESS, vol. 7, 2019, pages 31959 - 31970, XP011715773, DOI: 10.1109/ACCESS.2019.2903582
See also references of EP 3857506A4

KIM, Tae-hun et al. (KR)

View/Download PDF      PDF Help

Previous Patent: TRANSFER APPARATUS AND METHOD OF MANUFACTURING MICRO LED DISPLAY USING THE SAME

Next Patent: POLYOLEFIN-BASED RESIN COMPOSITION AND FOOD WRAPPING FILM USING SAME