Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
IMAGE PROCESSING MODEL GENERATING METHOD, PROCESSING METHOD, STORAGE MEDIUM, AND TERMINAL
Document Type and Number:
WIPO Patent Application WO/2021/179764
Kind Code:
A1
Abstract:
An image processing model generating method, a processing method, a storage medium and a terminal. The generating method comprises: inputting a first image in a preset training image set to a preset network model; and sequencing a preset model by means of a generated image generated by the preset network model and a second image corresponding to the first image, so as to obtain an image processing model. The image processing model is obtained by performing deep learning on a color cast-removal process of the training image set having multiple training image groups; each training image group comprises a first image and a second image, and the first image is a color cast image corresponding to the second image. Hence, deep learning is performed on the basis of the training image set to obtain a trained image processing model for color cast processing, such that color cast adjustment can be quickly performed on an image, thereby improving the color quality of the image and improving the image quality.

Inventors:
LI SONGNAN (CN)
ZHANG YU (CN)
YU DAHAI (CN)
Application Number:
PCT/CN2020/141932
Publication Date:
September 16, 2021
Filing Date:
December 31, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
TCL TECH GROUP CORP (CN)
International Classes:
G06T5/00; G06N3/04
Foreign References:
CN110223254A2019-09-10
CN110097512A2019-08-06
CN110602467A2019-12-20
CN110473154A2019-11-19
Other References:
MICHAËL GHARBI: "Deep Bilateral Learning for Real-Time Image Enhancement", 22 August 2017 (2017-08-22), pages 1 - 12, XP055533360, Retrieved from the Internet DOI: 10.1145/3072959.3073592
Attorney, Agent or Firm:
JOHNSON INTELLECTUAL PROPERTY AGENCY(SHENZHEN) (CN)
Download PDF: