Image domain conversion network based on generative adversarial networks (GAN) and conversion method

Abstract

The invention discloses an image domain conversion network based on generative adversarial networks (GAN) and a conversion method. The image domain conversion network includes a U-shaped generative network, an authenticity authentication network and a pairing authentication network. An image domain conversion process mainly includes the following steps: 1) training the U-shaped generative network,and establishing a network model of the U-shaped generative network; and 2) normalizing a to-be-converted image, and then input the image into the network model established through the step 1) to complete image domain conversion of the to-be-converted image. According to the image domain conversion network, an image domain conversion task of a local region in the image can be achieved, image local-domain conversion quality is high, judgment ability of the network is high, stability of image conversion is high, and authenticity of a generated image is greatly improved.

Description

technical field [0001] The invention relates to the technical field of image domain conversion, in particular to an image domain conversion network and conversion method based on a generative confrontation network. Background technique [0002] Image domain conversion is an important research direction in computer vision and has broad application prospects. At present, the emergence of Generative Adversarial Networks (GAN) has made remarkable achievements in the field of image generation, which also provides a new solution for image domain conversion. Using the generative confrontation network, the image is input and the network is generated to generate the image of the target domain. The training of the network is completed based on the game between the generation network and the discrimination network. The generative confrontation network was originally proposed as an unsupervised learning method. Through the game between the generative network and the discriminant networ...

AI Technical Summary

Problems solved by technology

Among them, although the unsupervised method no longer needs one-to-one paired training data, the conversion effect is worse than the supervised pix2pix network, and it is still aimed at the conversion of the overall image domain. In the existing image domain conversion, for the image The domain transformation task in the local area, and there is no dedicated GAN

Images