Image deblurring system and method based on dual control network

Abstract

The invention provides an image deblurring system and an image deblurring method based on a dual control network. The system comprises a coding module used for carrying out image feature extraction on an input image; the data module is used for performing degradation processing and further feature extraction processing according to the extracted image features; the control module is used for controlling the processing process of the data module; the decoding module is used for decoding according to the processed data to obtain reconstruction features; wherein a cyclic hopping connection is established between the encoding module and the decoding module, via which the output of the encoding module is added to the input of the decoding module, and the output of the decoding module is added to the input of the encoding module. According to the method, the effectiveness problem based on the deep learning network and the flexibility problem based on the model are improved through dual control, the image deblurring SSIM and PSNR indexes are greatly improved, and the visual effect is improved.

Description

technical field [0001] The present invention relates to image processing, in particular to an image deblurring system and method. Background technique [0002] Traditional image deblurring uses filtering methods to divide the image into different components, filter out the blur components that affect the image quality, and synthesize a clear image. With the development of artificial intelligence, deep learning for end-to-end processing of image restoration tasks has been extensively studied. By constructing a deep learning network architecture, the features that make up the clear image are continuously learned, and then the feature map is formed by comparing the fuzzy images, and finally the feature fusion restores the clear image. [0003] Most of the existing deep learning-based deblurring methods are based on the codec structure, adding an attention module at the output end to enhance the output features. This type of image deblurring method has a complex calculation pr...

AI Technical Summary

Problems solved by technology

This type of image deblurring method has a complex calculation process, a large amount of parameters, serious ringing effects, a large room for improvement in the restoration effect, and a lack of ability to identify blur kernels.

Images