Realistic real-time processing of anime portraits based on generative adversarial networks

Abstract Nowadays, more and more brands use interesting anime characters to promote and increase brand awareness. However, real-time and interesting promotional materials are also one of the key factors to attract people, so real-time processing of anime characters has also become an effective way to enhance brand awareness. In recent years, with the rapid development of deep learning, image style conversion based on AI technology has become a much-attended artificial intelligence application, but it also suffers from the disadvantages of complex model structure, slow conversion speed, and inconspicuous identity features, which need to be improved. In view of this, this paper proposes an Anime Portrait Realization (ARF-GAN) algorithm based on Generative Adversarial Network. This algorithm is based on the CGAN architecture and also uses the U-net network structure with jump connections to connect the encoder's feature maps directly to the decoder, which in turn enables the network to reconstruct the output data in a better way and the network architecture is more lightweight. It also introduces the CBAM module, which can enhance the model's expressive and generative capabilities without increasing the model's complexity, and improve the model's real-time image processing capability. In addition, this paper also compensates for the problem of image blurring brought by the original architecture by introducing the deblurring module. Based on Windows 10 environment and Python 3.7 programming language, and experiments on CartoonFace, DanBooru dataset show that the proposed ARF-GAN has a better generative effect for the task of realizing anime portraits, and comparing with different types of image generating models, it shows better accuracy and lower accuracy in several evaluation indexes such as PSNR, SSIM, and so on. better accuracy and lower time complexity. This makes it more suitable for brand advertisement promotion, so it has good application value for improving in brand awareness.