Neural saliency algorithm guide bi-directional visual perception style transfer

CAAI Transactions on Intelligence Technology

article

Chunbiao Zhu¹  Wei Yan¹  Xing Cai¹  Shan Liu²  Thomas H. Li¹  Ge Li¹ 

[1] Shenzhen Graduate School, Peking University;Tencent America;China and Advanced Institute of Information Technology, Peking University

关键词: visual perception;    feature extraction;    image segmentation;    image colour analysis;    object detection;    human visual system;    automatic visual perception style transfer;    novel saliency detection algorithm;    visual attention;    conventional style transfer algorithm;    image regions;    style transferring process;    artistic style transfer;    aesthetic perception;    neural saliency algorithm guide bi-directional visual perception style transfer;    B6135 Optical;    image and video signal processing;    C5260B Computer vision and image processing techniques;   

DOI  :  10.1049/trit.2019.0034

学科分类：数学（综合）

来源: Wiley

【 摘 要 】

The artistic style transfer of images aims to synthesise novel images by combining the content of one image with the style of another, which is a long-standing research topic and already has been widely applied in real world. However, defining the aesthetic perception from the human visual system is a challenging problem. In this study, the authors propose a novel method for automatic visual perception style transfer. First, they render a novel saliency detection algorithm to automatically perceive the visual attention of an image. Then, different from conventional style transfer algorithm in which style transferring is applied uniformly across all image regions, the authors apply a saliency algorithm to guide the style transferring process, enabling different types of style transferring to occur in different regions. Extensive experiments show that the proposed saliency detection algorithm and the style transfer algorithm are superior in performance and efficiency.

【 授权许可】

CC BY|CC BY-ND|CC BY-NC|CC BY-NC-ND