Research and implementation of fast image style transfer
Yi Zhang · 2023
Image style transfer refers to the process of merging the content of a source image with the style(s) of one or more reference images, thereby creating images that combine the original content with other styles. This dissertation focuses on using a convolutional neural network (CNN) to achieve this goal. The image style transfer is completed with data augmentation, a loss network, and an image transformation network. The VGG-19 network is used to extract features in the loss network, and the content loss function and style are optimized iteratively through gradient descent. Additionally, a custom residual module network is trained to enable a specific style conversion of the image. As a result, the final model shows significant improvement, with the final style loss reduced to 2000E+4, and the total loss reduced to 6000E+4, thus achieving good results.