IFFMStyle: High-Quality Image Style Transfer Using Invalid Feature Filter Modules

Image style transfer is a challenging problem in computer vision which aims at rendering an image into different styles. A lot of progress has been made to transfer the style of one painting of a representative artist in real time, whereas less attention has been focused on transferring an artist’s style from a collection of his paintings. This task requests capturing the artist’s precise style from his painting collection. Existing methods did not pay more attention on the possible disruption of original content details and image structures by texture elements and noises, which leads to the structure deformation or edge blurring of the generated images. To address this problem, we propose IFFMStyle, a high-quality image style transfer framework. Specifically, we introduce invalid feature filtering modules (IFFM) to the encoder–decoder architecture to filter the content-independent features in the original image and the generated image. Then, the content-consistency constraint is used to enhance the model’s content-preserving capability. We also introduce style perception consistency loss to jointly train a network with content loss and adversarial loss to maintain the distinction of different semantic content in the generated image. Additionally, we have no requirement for paired content image and style image. The experimental results show that the stylized image generated by the proposed method significantly improves the quality of the generated images, and can realize the style transfer based on the semantic information of the content image. Compared with the advanced method, our method is more favored by users.