EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer
This work addresses style transfer in computer vision and graphics, offering an incremental improvement over prior methods for generating more compatible stylized images.
The paper tackles the problem of arbitrary style transfer by proposing EFANet, which jointly aligns exchangeable features from content and style images to improve structured stylization, achieving better qualitative and quantitative results compared to existing methods.
Style transfer has been an important topic both in computer vision and graphics. Since the seminal work of Gatys et al. first demonstrates the power of stylization through optimization in the deep feature space, quite a few approaches have achieved real-time arbitrary style transfer with straightforward statistic matching techniques. In this work, our key observation is that only considering features in the input style image for the global deep feature statistic matching or local patch swap may not always ensure a satisfactory style transfer; see e.g., Figure 1. Instead, we propose a novel transfer framework, EFANet, that aims to jointly analyze and better align exchangeable features extracted from content and style image pair. In this way, the style features from the style image seek for the best compatibility with the content information in the content image, leading to more structured stylization results. In addition, a new whitening loss is developed for purifying the computed content features and better fusion with styles in feature space. Qualitative and quantitative experiments demonstrate the advantages of our approach.