Title:
METHOD AND DEVICE FOR TRAINING A SUPER-RESOLUTION NETWORK
Document Type and Number:
WIPO Patent Application WO/2022/092900
Kind Code:
A1
Abstract:
A method for training a super-resolution network may include obtaining a first image; generating, using a first machine learning model, a second image based on the first image; generating, using a second machine learning model, a third image, based on the second image and a first dataset of images; obtaining a training data set using the first image and the third image; and training the super-resolution network using the training data set.
More Like This:
JP2007256370 | REPRODUCING DEVICE |
WO/2023/016603 | METHOD FOR IMAGING A SURFACE OF A TURBOMACHINE AND DETECTING DAMAGE |
Inventors:
LEVINSHTEIN ALEKSAI (US)
SUN XINYU (US)
WANG HAICHENG (US)
BHASKARA VINEETH SUBRAHMANYA (US)
TSOGKAS STAVROS (US)
JEPSON ALLAN (US)
SUN XINYU (US)
WANG HAICHENG (US)
BHASKARA VINEETH SUBRAHMANYA (US)
TSOGKAS STAVROS (US)
JEPSON ALLAN (US)
Application Number:
PCT/KR2021/015450
Publication Date:
May 05, 2022
Filing Date:
October 29, 2021
Export Citation:
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06T3/40; G06N3/08; G06T5/20
Domestic Patent References:
WO2019220095A1 | 2019-11-21 |
Foreign References:
US20200111194A1 | 2020-04-09 | |||
US20180068430A1 | 2018-03-08 |
Other References:
ZHOU RUOFAN; SUSSTRUNK SABINE: "Kernel Modeling Super-Resolution on Real Low-Resolution Images", 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 27 October 2019 (2019-10-27), pages 2433 - 2443, XP033724079, DOI: 10.1109/ICCV.2019.00252
DMITRY ULYANOV , ANDREA VEDALDI , VICTOR LEMPITSKY: "Deep Image Prior", ARXIV, pages 1 - 23, XP055925717
DMITRY ULYANOV , ANDREA VEDALDI , VICTOR LEMPITSKY: "Deep Image Prior", ARXIV, pages 1 - 23, XP055925717
Attorney, Agent or Firm:
Y.P.LEE, MOCK & PARTNERS (KR)
Download PDF: