Abstract
The works of Gatys et al. demonstrated the capability of Convolutional Neural Networks (CNNs) in creating artistic style images. This process of transferring content images in different styles is called Neural Style Transfer (NST). In this paper, we re-implement image-based NST, fast NST, and arbitrary NST. We also explore to utilize ResNet with activation smoothing in NST. Extensive experimental results demonstrate that smoothing transformation can greatly improve the quality of stylization results.
Abstract (translated)
Gatys等人的一项研究表明，卷积神经网络（CNN）具备生成艺术风格图像的能力。这种将内容图像转换为不同风格的过程被称为神经样式迁移（NST）。在这篇论文中，我们重新实现了基于图像的NST、快速NST和任意NST。同时，我们也探索了在NST中使用带有激活平滑处理的ResNet的方法。大量的实验结果表明，通过平滑变换可以极大地提升样式的生成质量。
URL
https://arxiv.org/abs/2411.08014
