Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer

CVPR(2020)

引用 77|浏览138
暂无评分
摘要
This paper introduces a neural style transfer model to generate a stylized image conditioning on a set of examples describing the desired style. The proposed solution produces high-quality images even in the zero-shot setting and allows for more freedom in changes to the content geometry. This is made possible by introducing a novel Two-Stage Peer-Regularization Layer that recombines style and content in latent space by means of a custom graph convolutional layer. Contrary to the vast majority of existing solutions, our model does not depend on any pre-trained networks for computing perceptual losses and can be trained fully end-to-end thanks to a new set of cyclic losses that operate directly in latent space and not on the RGB images. An extensive ablation study confirms the usefulness of the proposed losses and of the Two-Stage Peer-Regularization Layer, with qualitative results that are competitive with respect to the current state of the art using a single model for all presented styles. This opens the door to more abstract and artistic neural image generation scenarios, along with simpler deployment of the model.
更多
查看译文
关键词
two-stage peer-regularization layer,stage peer-regularized feature recombination,neural style transfer model,arbitrary image style transfer,artistic neural image generation scenarios,abstract image generation scenarios,RGB images,cyclic losses,end-to-end thanks,perceptual losses,pre-trained networks,custom graph convolutional layer,latent space,content geometry,zero-shot setting,high-quality images,stylized image conditioning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要