Image processing method and device, storage medium and electronic equipment

By introducing a second encoder into the image processing model and using the first loss function for training constraints, the problem of the complexity of the low-quality image restoration process is solved, achieving efficient image sharpening and reducing model complexity, making it suitable for mobile terminals.

CN116206168BActive Publication Date: 2026-07-21BEIJING XIAOMI MOBILE SOFTWARE CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING XIAOMI MOBILE SOFTWARE CO LTD
Filing Date
2021-11-30
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

The existing technology for restoring low-quality blurry images to high-quality clear images is complex and inefficient, and is particularly difficult to deploy on mobile terminals.

Method used

A target image processing model is adopted, including a first encoder and a first decoder, and a second encoder is introduced. The degree of difference between the encoded vector and the encoded vector is calculated through a first loss function. The trained first encoder has the ability to reverse image mapping and remove blur degradation. The second encoder is used for constraints during model training, and the second encoder is removed during application to reduce complexity.

Benefits of technology

The training process improves the encoder's inverse mapping and blur removal capabilities while reducing the complexity of the target image processing model, making it suitable for deployment on mobile devices.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116206168B_ABST
    Figure CN116206168B_ABST
Patent Text Reader

Abstract

The present disclosure relates to an image processing method, device, storage medium and electronic equipment. The method comprises: obtaining a to-be-processed image; inputting the to-be-processed image into a target image processing model to obtain a target image corresponding to the to-be-processed image; wherein the target image processing model is obtained by training a preset image processing model according to a first loss function; the target image processing model comprises a first encoder and a first decoder, the output end of the first encoder is coupled with the input end of the first decoder, and the preset image processing model comprises the first encoder, the first decoder and a second encoder; the first encoder is configured to encode an input to-be-processed sample image into a first encoding vector, the second encoder is configured to encode an input target sample image into a second encoding vector, the target sample image corresponds to the to-be-processed sample image, and the first loss function is configured to calculate a first loss value of the first encoding vector and the second encoding vector.
Need to check novelty before this filing date? Find Prior Art