Image inpainting method and system based on antagonistic generation neural network

Abstract

The invention provides an image inpainting method and system based on antagonistic generation neural network, which comprises the following steps: firstly, constructing a self-encoder convolutional neural network (including encoder and encoding discriminator), a decoder (generator) convolutional neural network, a discriminator convolutional neural network, a global discriminator, and a local discriminator; Then, different loss functions are constructed for the five networks, and the whole network is trained by step-by-step training. Finally, when the network training is completed, the defect image is put into the network for repairing, and the result graph generated by the decoder (generator) is the final repairing result graph. The invention has the advantages that: the potential constraint of the image is kept and the image is thinned; an end-to-end image restoration network is implemented. The dependence of the repair network on the missing position mask information of the image iseliminated. The robustness in practical application is improved.

Description

technical field [0001] The invention belongs to computer and information service technology, in particular to a method and system for reasonably repairing missing digital images. Background technique [0002] With the development of the information age and the popularization of digital equipment, digital images, as the carrier of image data recording and transmission, have the characteristics of efficient information storage, intuitive expression, and easy editing, bringing unprecedented opportunities for image shooting, storage, processing, and communication. change. Digital images have widely existed in people's lives, and are growing at an alarming rate. Images are often damaged or blocked during shooting, storage, processing, and transmission, making the information stored in the image lose its integrity, and the pixels in the image information often have a strong correlation with each other, so we can The damaged or unoccluded image information restores the lost image...

AI Technical Summary

Problems solved by technology

However, for high-level semantic features, the distribution of texture features is extensive and complex, which is difficult to construct manually

[0014] The method based on the diffusion model is easy to apply to repair small-scale areas, but it cannot be applied to repair large-scale areas; the method based on texture synthesis and candidate filling area search can repair large-scale background textures to a certain extent, but the repair effect Relying on the texture library and unable to solve the situation with missing image semantics; the method based on deep learning can repair the image semantics, but the quality of the generated image cannot be compared with the original Figure 1 Additional processing is required

Images