Exploration and Practice of Artificial Intelligence Generative Art in Environmental Public Art

Applying AI generative art to the field of environmental public art can improve work efficiency, save money, reduce costs and increase profits. In this paper, an optimized generative AI technique is proposed by combining the high-level semantic features of images and the underlying color features, while introducing the Gestalt visual perception theory. The performance of the optimized generative AI technique is evaluated by conducting a questionnaire survey on 50 subjects. Increasing the test sample capacity and analyzing the survey data, it is concluded that the mean value of the scores of perceived quality, perceived value, perceived cost, perceived risk, social impact, media barriers, and willingness to accept are all above 4, and the mean value of technology anxiety is the lowest at 3.832. This paper provides reference significance for the production and dissemination of image content of AI-generated art in the field of environmental public art.