CVJan 18, 2016
Content Aware Neural Style Transfer
arXiv:1601.04568v132 citations
Originality Synthesis-oriented
AI Analysis
This work addresses style transfer for visual media, but it is incremental as it builds on existing neural network methods.
The paper tackles the problem of style transfer for paintings and photos with similar content using a pre-trained neural network, achieving better results than prior work, and it shows through experiments that style and content are not fully separable in neural networks.
This paper presents a content-aware style transfer algorithm for paintings and photos of similar content using pre-trained neural network, obtaining better results than the previous work. In addition, the numerical experiments show that the style pattern and the content information is not completely separated by neural network.