Abstract
Due to the high diversity of image styles, the scalability to various styles plays a critical role in real-world applications. To accommodate a large amount of styles, previous multi-style transfer approaches rely on enlarging the model size while arbitrary-style transfer methods utilize heavy backbones. However, the additional computational cost introduced by more model parameters hinders these methods to be deployed on resource-limited devices. To address this challenge, in this paper, we develop a style transfer framework by decoupling the style modeling and transferring. Specifically, for style modeling, we propose a style representation learning scheme to encode the style information into a compact representation. Then, for style transferring, we develop a style-aware multi-style transfer network (SaMST) to adapt to diverse styles using pluggable style representations. In this way, our framework is able to accommodate diverse image styles in the learned style representations without introducing additional overhead during inference, thereby maintaining efficiency. Experiments show that our style representation can extract accurate style information. Moreover, qualitative and quantitative results demonstrate that our method achieves state-of-the-art performance in terms of both accuracy and efficiency. The codes are available in this https URL.
Abstract (translated)
由于图像风格的多样性非常高，因此在实际应用中，能够适应各种风格的可扩展性起着关键作用。为了应对大量的不同风格，以往的多风格转移方法依赖于扩大模型规模，而任意风格转移方法则使用重型骨干网络（backbone）。然而，由更多模型参数引入的额外计算成本阻碍了这些方法在资源受限设备上的部署。 为了解决这一挑战，在本文中我们开发了一个通过解耦样式建模和转换来实现样式的迁移框架。具体来说，在样式建模方面，我们提出了一种风格表示学习方案，用以将风格信息编码成紧凑的表示形式。然后，对于样式转移，我们开发了一种基于可插拔样式表示的感知多风格传输网络（SaMST），以此适应多样化的样式需求。通过这种方式，我们的框架能够在不增加推理过程额外开销的情况下容纳各种图像样式，并保持了效率。 实验表明，我们的样式表示能够准确地提取出风格信息。此外，定性和定量结果均显示，我们的方法在精度和效率方面都达到了最先进的性能水平。代码可以在提供的链接中找到：[此 https URL]。
URL
https://arxiv.org/abs/2503.20368
