Title:
ARTIFICIAL-INTELLIGENCE-BASED IMAGE INPAINTING METHOD AND DEVICE
Document Type and Number:
WIPO Patent Application WO/2022/080680
Kind Code:
A1
Abstract:
An operation method for image inpainting comprises the steps of: sorting objects included in a first image, on the basis of information about respective pixels of the first image; determining, from among the objects, a first object to be corrected; setting a boundary between a second object and a third object in an area corresponding to the first object removed from the first image; and recovering, on the basis of pixel information about the second object and the third object, an area corresponding to the first object, with respect to the boundary. According to the present invention, the images are analyzed on the basis of artificial intelligence so that the images are sorted by object, and after at least one object is removed from the sorted objects, the images are recovered so that an easier image inpainting service can be provided to the user.
More Like This:
Inventors:
LEE WON SEOP (KR)
PARK JEONG SEON (KR)
KANG DONG YEON (KR)
JIN AH JUNG (KR)
PARK JEONG SEON (KR)
KANG DONG YEON (KR)
JIN AH JUNG (KR)
Application Number:
PCT/KR2021/012502
Publication Date:
April 21, 2022
Filing Date:
September 14, 2021
Export Citation:
Assignee:
CNAI CO LTD (KR)
International Classes:
G06T5/00; G06T7/11; G06T7/13
Foreign References:
| KR20190078543A | 2019-07-04 | |||
| KR20150009184A | 2015-01-26 | |||
| US20110103644A1 | 2011-05-05 | |||
| US20080238942A1 | 2008-10-02 |
Other References:
YANG, CHAO ET AL.: "High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis", CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR, 21 July 2017 (2017-07-21), pages 4076 - 4084, XP033249760, DOI: 10.1109/CVPR.2017.434
Attorney, Agent or Firm:
SHIN, Moo Yun (KR)
Download PDF: