期刊
VISUAL COMPUTER
卷 36, 期 2, 页码 317-331出版社
SPRINGER
DOI: 10.1007/s00371-018-1609-4
关键词
Photographic style transfer; Deep learning; Photorealism preservation; Image processing
资金
- European Commission under FP7 MarieCurie IRSES project AniNex [612627]
- China Scholarship Council
- Visual Media Research Centre at Tsinghua University
Image style transfer has attracted much attention in recent years. However, results produced by existing works still have lots of distortions. This paper investigates the CNN-based artistic style transfer work specifically and finds out the key reasons for distortion coming from twofold: the loss of spatial structures of content image during content-preserving process and unexpected geometric matching introduced by style transformation process. To tackle this problem, this paper proposes a novel approach consisting of a dual-stream deep convolution network as the loss network and edge-preserving filters as the style fusion model. Our key contribution is the introduction of an additional similarity loss function that constrains both the detail reconstruction and style transfer procedures. The qualitative evaluation shows that our approach successfully suppresses the distortions as well as obtains faithful stylized results compared to state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据