A study of utilizing computer-generated art methods to enhance creative expression in art education

The emergence of techniques such as Generative Adversarial Networks (GANs) has given the possibility of continuous enhancement of computer generated art methods. The article proposes an approach to art image style migration and generation based on generative adversarial networks. After summarizing the applied research on computer-generated art, the article then proceeds with an in-depth study and analysis of GANs and key algorithms for real-time image style migration, and furthermore proposes an unconditional generative adversarial network architecture, Draw GAN. After applying the method proposed in this article to art education, it was found that the experimental scores of students in the experimental group were 0.4 higher than those of the control group in terms of creative strategies, i.e., the application of the method in this article has an enhancing effect on the creative expression ability of students in the experimental group. The article provides a new perspective on the application of computer-generated generative art methods in art education.