Image defogging method and system based on adaptive convolution and texture prior

By combining adaptive multi-scale convolution and texture restoration modules, the problem of poor image dehazing in existing technologies is solved, and effective restoration of high-frequency details and improvement of image clarity are achieved.

CN121998873APending Publication Date: 2026-05-08HEFEI UNIV OF TECH
5 Cites 0 Cited by

Patent Information

Application Number
CN202610458719.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-09
Publication Date
2026-05-08

AI Technical Summary

Technical Problem

Existing image dehazing methods are insufficient in restoring high-frequency detail information when dealing with non-uniform fog and extremely dense fog. They are unable to distinguish between dense fog and thin fog regions, resulting in dehazing failure and smooth restoration results with loss of texture and edge information.

Method used

A combination of an adaptive multi-scale convolution module and a texture restoration module is adopted. The adaptive multi-scale convolution module dynamically adjusts the receptive field according to the fog concentration and scene structure, and performs texture restoration by combining a pre-trained discrete feature codebook. A clear image is then generated by the decoder.

Benefits of technology

It improves image dehazing, restores high-frequency texture and edge information, and generates clearer images with higher visual quality.

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

Abstract

The invention discloses an image defogging method and system based on adaptive convolution and texture prior, and belongs to the technical field of computer vision. The method comprises the following steps: acquiring an original image; inputting the original image into a self-adaptive multi-scale convolution module in the defogging model for processing to obtain a coding feature map; according to a discrete feature codebook obtained through pre-training, optimizing the coding feature map through a texture restoration module in a defogging model to obtain a texture restoration feature map; and processing the texture restoration feature map through a decoder in a defogging model to obtain a defogged target image. According to the scheme, on one hand, the feature extraction effect of non-uniform fog spots in a complex real scene is improved through the adaptive multi-scale convolution module, and on the other hand, the smoothed texture in the feature extraction process is restored through the texture restoration module, so that the defogging effect of the image is improved.
Need to check novelty before this filing date? Find Prior Art