Image restoration method, device and equipment

Abstract

An image restoration method includes generating a plurality of damaged images from an image to be restored, and determining corresponding intact images in positions where the damaged images are, the damaged images being images fused by the damaged image and the intact images; using the generated plurality of damaged images and the corresponding intact images in the positions where the damaged images are as training samples, importing a generator of a generative adversarial network, performing feature fusion on an encoder and a decoder in the generator, and learning features of the image to berestored through the generative adversarial network; and restoring the image to be restored according to the trained generative adversarial network. The image to be restored is restored according to the trained generative adversarial network, the problem that a template for an area to be restored needs to be used when the image is processed can be solved, and through feature fusion of the encoderand decoder in the generator in the generative adversarial network, a large-area damaged module can be effectively restored.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to an image restoration method, device and equipment. Background technique [0002] Our country has a long history, and the ancients left a large number of ancient paintings of literati. These ancient paintings have gone through hundreds of thousands of years and are of great value for understanding the development of human civilization. However, due to natural weathering or man-made destruction, they have been lost or incomplete to varying degrees, seriously affecting their visual effects and appreciation value. Therefore, repairing them is a very valuable and meaningful work. [0003] At present, image inpainting is mainly divided into two categories: pixel-based inpainting algorithms and image block-based inpainting algorithms. Among them, the pixel-based repair algorithm operates on pixels and is generally used to repair small-area damaged modules. algorithm etc. ...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention provides an image repair method, device and equipment to solve the problem in the prior art that the user needs to provide a template for the area to be repaired, and when the damaged area is large, the repair of the damaged module of the texture image will be difficult. Produces a smooth effect, while producing a certain degree of blurring

Images