Edge Enhanced Image Style Transfer via Transformers
This addresses the trade-off between content and style in image style transfer for applications like digital art and media, but it is incremental as it builds on existing transformer-based approaches.
The paper tackles the problem of preserving content details while transferring style patterns in arbitrary image style transfer, achieving comparable performance to state-of-the-art methods and alleviating content leak issues.
In recent years, arbitrary image style transfer has attracted more and more attention. Given a pair of content and style images, a stylized one is hoped that retains the content from the former while catching style patterns from the latter. However, it is difficult to simultaneously keep well the trade-off between the content details and the style features. To stylize the image with sufficient style patterns, the content details may be damaged and sometimes the objects of images can not be distinguished clearly. For this reason, we present a new transformer-based method named STT for image style transfer and an edge loss which can enhance the content details apparently to avoid generating blurred results for excessive rendering on style features. Qualitative and quantitative experiments demonstrate that STT achieves comparable performance to state-of-the-art image style transfer methods while alleviating the content leak problem.