An Image Domain Transformation Network and Transformation Method Based on Generative Adversarial Networks

Abstract

The invention discloses an image domain conversion network and a conversion method based on a generative confrontation network, including a U-shaped generation network, a true-false identification network, and a pair identification network. The image domain conversion process mainly includes the following steps: 1), training U-shaped Generate a network and establish a network model of a U-shaped generating network; 2) input the image to be converted into the network model established in step 1) after normalization processing, and complete the image domain conversion of the image to be converted; the present invention can realize The task of image domain conversion in local areas, and the quality of image local domain conversion is high, the network judgment ability is strong, and the stability of image conversion is strong, which greatly improves the authenticity of generated images.

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