Image snow removal method based on multi-frequency enhanced degradation perception routing attention

By introducing dual-frequency enhancement and routing self-attention technology in the field of image snow removal, the problem of incomplete removal of large-scale snowflakes and difficulty in distinguishing between snowflakes and background is solved, and more efficient image snow removal effect and more complete detail recovery is achieved.

CN119693255AInactive Publication Date: 2025-03-25SICHUAN UNIV
2 Cites 5 Cited by

Patent Information

Application Number
CN202411767652.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-04
Publication Date
2025-03-25
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art is difficult to effectively remove large-scale snowflakes in the field of image snow removal, resulting in the loss of important information. At the same time, it is difficult to distinguish between snowflakes and background information in scenes with similar snowflake shapes and background information, affecting the quality of snow removal effects and the details of recovery.

Method used

A method of image snow removal based on dual-frequency enhancement is proposed. High and low-frequency features are enhanced and fused through multi-frequency enhancement modules, and global dependence modeling of degraded areas is combined with degraded perception routing attention modules to enhance the ability to identify the differences between snowflakes and background textures.

Benefits of technology

In complex snow degradation scenarios, snowflakes are removed more thoroughly, while retaining more scene information, improving the accuracy and effect of image snow removal, and solving the problem of incomplete removal of large-scale snowflake degradation areas.

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

Abstract

The invention provides an image snow removal method based on dual-frequency domain enhancement, which adopts a discrete wavelet transform technology to decompose high and low frequencies and fuse high-frequency enhancement features and low-frequency enhancement features after the high and low frequencies pass through a feature enhancement network so as to enhance the recovery of detail textures of a snowflake-degraded image. According to the method provided by the invention, the high-frequency characteristics of the snow degradation image are enhanced by using a differential convolutional network, and meanwhile, the serious degradation influence caused by large-scale snowflakes is reduced by using a low-frequency enhancement network, so that the performance of the snow degradation image in different frequency domains during snowflake removal and image restoration is improved. And meanwhile, global modeling is carried out on a seriously degraded area through a degradation sensing routing attention module, so that seriously degraded snowflakes are further removed more thoroughly.
Need to check novelty before this filing date? Find Prior Art