Multi-scale and multi-feature fusion feature pyramid network blind restoration method

Abstract

The invention provides a multi-scale and multi-feature fusion feature pyramid network blind restoration method, which is used for solving the technical problems of poor restoration performance and poor robustness of an existing restoration method. The method comprises the following steps: firstly, acquiring N groups of clear images and blurred images from a data set; secondly, constructing a generative adversarial network model of a feature pyramid network and a dual-scale discriminator network; alternately training the feature pyramid network and the discriminator network by using N groups ofclear images and blurred images, and obtaining a final generative adversarial network model after a balance point is reached; and finally, inputting the blurred image to be processed into the final generative adversarial network model, and outputting a clear image. According to the method, the feature pyramid network is combined with the dual-scale discriminator, detail information loss is greatly avoided while the training speed is increased, finally, a multi-scale structure similarity loss function is introduced to further restrain image generation, and stable and high-quality restoration of the complex blurred image is achieved.

Description

technical field [0001] The invention relates to the technical field of blind restoration in the field of image processing and computer vision, in particular to a multi-scale and multi-feature fusion feature pyramid network blind restoration method. Background technique [0002] Blurred images are often seen in daily life. Due to the influence of imaging distance, imaging device resolution, camera shake and other factors, the image often degrades during the acquisition process, which leads to the occurrence of image blur, the most common of which is motion blur , severely restricts the development of medical imaging, traffic monitoring and target tracking, so it is particularly important to restore blurred images. [0003] When the blurred image is actually restored, the blur kernel is usually unknown, and only some prior information of the degraded image can be used to optimally estimate the original image under some restrictive rules. This method is called blind restoration...

AI Technical Summary

Problems solved by technology

[0007] In view of the deficiencies in the above-mentioned background technology, the present invention proposes a multi-scale and multi-feature fusion feature p

Images