Unsupervised image super-resolution fuzzy kernel estimation method and terminal

Abstract

The invention discloses an unsupervised image super-resolution fuzzy kernel estimation method and a terminal, and the method comprises the steps: obtaining an original input image, carrying out the augmentation of the original input image, and outputting a plurality of images; obtaining any image in the plurality of images, and performing down-sampling through an encoder to obtain a down-sampled image; according to the down-sampled image and the original input image, closing the block distribution between the down-sampled image and the original input image through a discriminator; performing up-sampling on the down-sampled image through a decoder to obtain the size of an original input image to obtain a reconstructed image; extracting blurred kernels of the plurality of images after the augmentation operation through an encoder, and obtaining a final blurred kernel after average processing. According to the method, the blurred kernel is estimated by learning the internal information ofthe image through the encoder, and the estimated blurred kernel is corrected through the feedback of the decoder, so that the accuracy of blurred kernel estimation is improved, and the super-resolution performance of the image in an unsupervised scene is improved.

Description

Technical field[0001]The present invention relates to the technical field of computer applications, in particular to an unsupervised image super-resolution blur kernel estimation method and terminal.Background technique[0002]Many existing deep learning-based image super-resolution methods are trained on large-scale simulation data sets, and the models trained in this way have general generalization ability in real scenes. For existing unsupervised image super-resolution methods, blur kernel estimation is a very important step. Estimating a more accurate blur kernel for the input image can effectively improve the performance of unsupervised image super-resolution, while the existing blur kernel The estimation method only considers the image down-sampling process, but does not use the further up-sampling process, and it is difficult to estimate a very accurate blur kernel.[0003]That is to say, the existing unsupervised blur kernel estimation method ignores the effect of the image upsa...

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to provide an unsupervised image super-resolution blur kernel estimation method and terminal, aiming to solve the problem that it is difficult to estimate a very accurate blur kernel in the prior art

Images