期刊论文

Zhao, Hui-Huang

英文

IEEE ACCESS

2169-3536

2019

7

85573-85580

10.1109/ACCESS.2019.2922554

This work was supported in part by the National Natural Science Foundation of China under Grant 61503128 and Grant 61772179, in part by the Science and Technology Plan Project of Hunan Province under Grant 2016TP1020, in part by the Scientific Research Fund of Hunan Provincial Education Department under Grant 16C0226, Grant 17C0223, and Grant 18A333, in part by the Hengyang Guided Science and Technology Projects and Application-Oriented Special Disciplines under Grant Hengkefa [2018]60-31, in part by the Double First-Class University Project of Hunan Province under Grant Xiangjiaotong [2018]469, in part by the Hunan Province Special Funds of Central Government for Guiding Local Science and Technology Development under Grant 2018CT5001, and in part by the Subject Group Construction Project of Hengyang Normal University under Grant 18XKQ02.

本校为第一且通讯机构

This paper presents a new image synthesis method for image style transfer. For some common methods, the textures and colors in the style image are sometimes applied inappropriately to the content image, which generates artifacts. In order to improve the results, we propose a novel method based on a new strategy that combines both local and global style losses. On the one hand, a style loss function based on a local approach is used to keep the style details. On the other hand, another style loss function based on global measures is used to capture more global structural information. The result...