Title:
IMAGE ENHANCEMENT METHOD AND IMAGE ENHANCEMENT SYSTEM BASED ON GENERATIVE ADVERSARIAL MODEL
Document Type and Number:
WIPO Patent Application WO/2023/159670
Kind Code:
A1
Abstract:
Disclosed in the present invention are an image enhancement method and image enhancement system based on a generative adversarial model. The image enhancement system comprises an acquisition unit, a training unit and an enhancement unit, wherein the acquisition unit is configured to acquire a first image of a travel environment that is captured by a camera of a first vehicle, and a second image of a travel environment that is captured by a camera of a second vehicle; the training unit is configured to train a generative adversarial model by using the first image, so as to obtain an image enhancement model; and the enhancement unit is configured to enhance the second image by means of inputting the second image into the image enhancement model, so as to improve the image quality of the second image.
More Like This:
Inventors:
ZENG HUAJIE (CN)
FANG YIXIANG (CN)
FANG YIXIANG (CN)
Application Number:
PCT/CN2022/079267
Publication Date:
August 31, 2023
Filing Date:
March 04, 2022
Export Citation:
Assignee:
ZENG HUAJIE (CN)
International Classes:
G06N3/04; G06T5/00
Foreign References:
| CN110570358A | 2019-12-13 | |||
| CN106740708A | 2017-05-31 | |||
| CN110163235A | 2019-08-23 | |||
| CN114037053A | 2022-02-11 | |||
| CN113496472A | 2021-10-12 | |||
| US20210158570A1 | 2021-05-27 |
Attorney, Agent or Firm:
BEIJING JUNHENG INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)
Download PDF: