Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
GENERATION METHOD, SYSTEM AND APPARATUS CAPABLE OF VISUAL RESOLUTION ENHANCEMENT, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/242029
Kind Code:
A1
Abstract:
A generation method, system and apparatus capable of visual resolution enhancement, and a storage medium. An acquired low-resolution single image to be processed is subjected to resolution processing by means of a single-image training model established by using training samples and a preset loss function, which training samples contain a high-resolution single image sample, a low-resolution single image sample and corresponding image description information samples thereof, such that the effect of restoring the low-resolution single image to a high-resolution single image can be accurately and efficiently realized. A single image having a higher resolution can be acquired on the basis of specific image description information prior, and high-frequency information of the single image can be restored, such that an output high-resolution single image contains more texture structure details, and the definition of the single image is thus improved. The present invention can be widely applied to the technical field of image processing.

Inventors:
JIN LONGCUN (CN)
LU SHENGLIN (CN)
Application Number:
PCT/CN2021/126019
Publication Date:
November 24, 2022
Filing Date:
October 25, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
OPT MACHINE VISION TECH CO LTD (CN)
International Classes:
G06T3/40
Foreign References:
CN113139907A2021-07-20
CN109615582A2019-04-12
CN111583112A2020-08-25
CN112699844A2021-04-23
CN111340708A2020-06-26
US20190304063A12019-10-03
Other References:
JIAYU QIN: "Research on Multi-scale Sub-networks and Combined Prior Information Single Image Super-resolution", MASTER THESIS, no. 2, 27 June 2020 (2020-06-27), CN, pages 1 - 82, XP093009576, DOI: 10.27151/d.cnki.ghnlu
Attorney, Agent or Firm:
UNITALEN ATTORNEYS AT LAW (CN)
Download PDF: