Target domain oriented unsupervised image conversion method based on generative adversarial network

Abstract

The invention provides a target domain oriented unsupervised image conversion method based on a generative adversarial network, and belongs to the field of computer vision. The target domain orientedunsupervised image conversion method is used for realizing an unsupervised cross-domain image-to-image conversion task, and belongs to the field of computer vision. According to the target domain oriented unsupervised image conversion method, a self-encoding reconstruction network is designed, and hierarchical representation of a source domain image is extracted by minimizing reconstruction loss of the source domain image; meanwhile, through a weight sharing strategy, the weights of network layers for encoding and decoding high-level semantic information in two groups of generative adversarialnetworks in the network model are shared, so that the output image can keep the basic structure and characteristics of the input image; and then, the two discriminators are respectively used for discriminating whether the input image is a real image or a generated image in respective fields. According to the target domain oriented unsupervised image conversion method, unsupervised cross-domain image conversion can be effectively carried out, and a high-quality image is generated. Experiments prove that the method provided by the invention obtains a good result on standard data sets such as CelebA and the like.

Description

technical field [0001] The invention belongs to the field of computer vision and relates to an unsupervised image conversion method based on a generation confrontation network. Background technique [0002] With the popularization of mobile devices and the rapid growth of Internet bandwidth, graphic image data has shown an explosive growth, and they carry a large amount of information to be mined. In recent years, research in the field of computer vision has developed rapidly, especially with the development of generative adversarial networks, the problem of image translation has also attracted extensive attention. [0003] Image transformation refers to converting an image from one representational scene to another while keeping the content of the image unchanged. Many problems in the fields of computer vision, computer graphics and image processing can actually be understood as image conversion problems. For example, image coloring can be regarded as converting grayscale ...

AI Technical Summary

Problems solved by technology

[0015] Aiming at the problems that the traditional method requires paired data and GAN itself is difficult to train, the present invention proposes a GAN-based target domain-oriented unsupervised image conversion method to realize unsupervised image conversion

Images