用激活平滑提升神经风格迁移图像质量
Artistic Neural Style Transfer Algorithms with Activation Smoothing
- 在ResNet中引入激活平滑技术改善风格迁移
- 实验表明平滑处理显著提升图像视觉质量
- 适合关注图像生成质量的开发者与研究者
Gatys等人的工作展示了卷积神经网络（CNN）生成艺术风格图像的能力。将内容图像转换为不同风格的过程称为神经风格迁移（NST）。本文重新实现了基于图像的NST、快速NST以及任意风格迁移。同时探索了在NST中使用带激活平滑的ResNet。大量实验结果表明，激活平滑能显著提升风格化结果的质量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。