SALIENCY-GUIDED IMAGE STYLE TRANSFER

被引:5
作者
Liu, Xiuwen [1 ,2 ]
Liu, Zhi [1 ,2 ]
Zhou, Xiaofei [3 ]
Chen, Minyu [1 ,2 ]
机构
[1] Shanghai Univ, Shanghai Inst Adv Commun & Data Sci, Shanghai 200444, Peoples R China
[2] Shanghai Univ, Sch Commun & Informat Engn, Shanghai 200444, Peoples R China
[3] Hangzhou Dianzi Univ, Inst Informat & Control, Hangzhou 310018, Zhejiang, Peoples R China
来源
2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW) | 2019年
基金
中国国家自然科学基金;
关键词
Style transfer; saliency detection; fusion; TEXTURE SYNTHESIS; TREE;
D O I
10.1109/ICMEW.2019.00019
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we propose an automatic saliency-guide style transfer method, which deploys style transfer to the salient object in an image. Our method can generate a new artwork form of image, which aggregates the characteristics of real-world images and artistic images. First, the existing style transfer method is utilized to combine the content of an arbitrary real-world image with the appearance of a well-known artwork, and to produce the stylized image with high perceptual quality. Then, the saliency map of real-world image is used to fuse the real-world image and the stylized image. In this way, the fusion image not only contains the style of artwork but also highlights the salient object. Finally, the saliency-based refinement is employed to improve the quality of object boundaries, and to enable the stylized object blends into the surroundings naturally. Experimental results demonstrate the effectiveness of the proposed saliency-guided image style transfer method.
引用
收藏
页码:66 / 71
页数:6
相关论文
共 19 条
  • [1] [Anonymous], 2016, P IEEE C COMPUTER VI
  • [2] Fast texture transfer
    Ashikhmin, M
    [J]. IEEE COMPUTER GRAPHICS AND APPLICATIONS, 2003, 23 (04) : 38 - 43
  • [3] Bhat P, 2008, LECT NOTES COMPUT SC, V5303, P114, DOI 10.1007/978-3-540-88688-4_9
  • [5] Castillo C, 2017, INT CONF ACOUST SPEE, P1348, DOI 10.1109/ICASSP.2017.7952376
  • [6] Chen T.Q., 2016, ARXIV161204337
  • [7] Efros A. A., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1033, DOI 10.1109/ICCV.1999.790383
  • [8] Efros AA, 2001, COMP GRAPH, P341, DOI 10.1145/383259.383296
  • [9] Gatys L. A., 2017, CVPR, P3985
  • [10] Image analogies
    Hertzmann, A
    Jacobs, CE
    Oliver, N
    Curless, B
    Salesin, DH
    [J]. SIGGRAPH 2001 CONFERENCE PROCEEDINGS, 2001, : 327 - 340