期刊论文

Zhao, Huihuang

英文

Computers & Electrical Engineering

0045-7906

2020

85

106655

10.1016/j.compeleceng.2020.106655

This work was supported by National Natural Science Foundation of China [grant number 61733004, 61503128, 61602402, 61573133], Science and Technology Plan Project of Hunan Province [grant number 2016TP1020], Scientific Research Fund of Hunan Provincial Education Department [grant number 18A333], Hengyang guided science and technology projects and Application-oriented Special Disciplines [grant number Hengkefa [2018]60-31], Double First-Class University Project of Hunan Province [grant number Xiangjiaotong [2018]469], Scientific and Technological Development Project of Hengyang City [grant number (2018)No.60-31], Postgraduate Scientific Research Innovation Project of Hunan Province [grant number CX20190998], Degree & Postgraduate Education Reform Project of Hunan Province (grant number 2019JGYB266), Postgraduate Teaching Platform Project of Hunan Province [grant number Xiangjiaotong [2019]370-321). We would like to thank NVIDIA for the GPU donation.

本校为通讯机构

When standard neural style transfer approaches are used in portrait style transfer, they often inappropriately apply textures and colours in different regions of the style portraits to the content portraits, leading to unsatisfied transfer results. This paper presents a portrait style transfer method to transfer the style of one image to another. It first proposes a combined segmentation method for the portrait parts, which segments both the style portrait and the content portrait into masks of seven parts automatically, including background, f...