DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfer
This addresses the problem of limited output variety in style transfer for researchers and practitioners, though it is incremental as it builds on existing patch-based methods.
The paper tackles the lack of diversity in patch-based style transfer methods by proposing DivSwapper, a plug-and-play module that generates multiple stylized outputs, showing superiority in diversity, quality, and efficiency compared to state-of-the-art algorithms.
Gram-based and patch-based approaches are two important research lines of style transfer. Recent diversified Gram-based methods have been able to produce multiple and diverse stylized outputs for the same content and style images. However, as another widespread research interest, the diversity of patch-based methods remains challenging due to the stereotyped style swapping process based on nearest patch matching. To resolve this dilemma, in this paper, we dive into the crux of existing patch-based methods and propose a universal and efficient module, termed DivSwapper, for diversified patch-based arbitrary style transfer. The key insight is to use an essential intuition that neural patches with higher activation values could contribute more to diversity. Our DivSwapper is plug-and-play and can be easily integrated into existing patch-based and Gram-based methods to generate diverse results for arbitrary styles. We conduct theoretical analyses and extensive experiments to demonstrate the effectiveness of our method, and compared with state-of-the-art algorithms, it shows superiority in diversity, quality, and efficiency.