Image defogging model training method and image defogging processing method and device

By combining the content-aware and recursive interactive Transformer module with the multi-scale frequency domain attention module, the image dehazing model solves the problem of insufficient recovery of low-frequency foggy parts and high-frequency details in existing technologies, and achieves high-quality dehazing effect.

CN121053014APending Publication Date: 2025-12-02CHINA TELECOM CORP LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202511166005.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-08-19
Publication Date
2025-12-02

AI Technical Summary

Technical Problem

Existing image dehazing algorithms are poor at processing low-frequency foggy parts and restoring high-frequency details, resulting in poor image quality after dehazing. They are also computationally complex and prone to producing halo effects.

Method used

An image dehazing model is adopted, which combines a content-aware and recursive interactive Transformer module with a multi-scale frequency domain attention module. Through iterative training, the global context feature extraction capability is improved, which can efficiently identify and attenuate low-frequency energy related to haze and restore high-frequency details.

Benefits of technology

It improves the quality and detail retention of dehazed images, avoids halo and color distortion, and enhances visual clarity and image quality.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an image defogging model training method and an image defogging processing method and device. The image defogging model training method comprises the following steps: acquiring a training sample set and a sample label set; an initial network model is constructed, and the model at least comprises M Transformer modules which are used for carrying out global context feature extraction on the foggy image and are combined with content perception and recursive interaction, and a multi-scale frequency domain attention module which is used for carrying out frequency domain feature extraction on global context feature maps output by the M Transformer modules which are combined with content perception and recursive interaction, m is a positive integer; and performing iterative training on the initial network model by using the training sample set and the sample label set to obtain an image defogging model. The image defogging method and device solve the technical problem that the defogged image is poor in quality due to the fact that a related image defogging model is poor in capability of processing a low-frequency foggy part and recovering high-frequency details.
Need to check novelty before this filing date? Find Prior Art