Single image super-resolution reconstruction method based on conditional generative adversarial network

Abstract

The invention discloses a single image super-resolution reconstruction method based on a conditional generative adversarial network. A judgment condition, namely an original real image, is added intoa judger network of the generative adversarial network. A deep residual error learning module is added into a generator network to realize learning of high-frequency information and alleviate the problem of gradient disappearance. The single low-resolution image is input to be reconstructed into a pre-trained conditional generative adversarial network, and super-resolution reconstruction is performed to obtain a reconstructed high-resolution image; learning steps of the conditional generative adversarial network model include: learning a model of the conditional adversarial network; inputtingthe high-resolution training set and the low-resolution training set into a conditional generative adversarial network model, using pre-trained model parameters as initialization parameters of the training, judging the convergence condition of the whole network through a loss function, obtaining a finally trained conditional generative adversarial network model when the loss function is converged,and storing the model parameters.

Description

technical field [0001] The invention relates to a single image super-resolution reconstruction method based on a conditional generation confrontation network, which belongs to the field of image processing, in particular to a super-resolution reconstruction method. Background technique [0002] Single image super-resolution (SISR) aims to recover a high-resolution image (HR) from a single low-resolution image (LR). This has direct applications in many fields such as HDTV, medical imaging, satellite imaging, face recognition and video surveillance. At present, people have higher and higher requirements for images, especially in terms of clarity. Improving image clarity purely from the hardware aspect is not only costly but also technically reaches a certain bottleneck. Improve the image resolution from the software, to a certain extent overcome the problem of insufficient hardware. Therefore, image super-resolution reconstruction has become one of the research hotspots. ...

AI Technical Summary

Problems solved by technology

A Super-Resolution Using a Generative Adversarial Network (SRGAN) algorithm based on a Generative Adversarial Network (SRGAN) is proposed. Although this game-like optimized SRGAN can generate high-quality images, the details are poor, and using this network Training is too free

The input of the GAN model lacks constraints. For larger input pictures or more pixels, the training will collapse, making the GAN uncontrollable.

In addition, SRGAN training uses a large number of training data sets, and the computer hardware configuration is relatively high, which is not conducive to the popularization of academic research and industrial applications

Images