Visual resource extraction and artistic communication model design based on improved CycleGAN algorithm.

ABSTRACT: Through the application of computer vision and deep learning methodologies, real-time style transfer of images becomes achievable. This process involves the fusion of diverse artistic elements into a single image, resulting in the creation of innovative pieces of art. This article centers its focus on image style transfer within the realm of art education and introduces an ATT-CycleGAN model enriched with an attention mechanism to enhance the quality and precision of style conversion. The framework enhances the generators within CycleGAN. At first, images undergo encoder downsampling before entering the intermediate transformation model. In this intermediate transformation model, feature maps are acquired through four encoding residual blocks, which are subsequently input into an attention

SUBMITTER: Yang A 

PROVIDER: S-EPMC11041928 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature