Two-phase Hair Image Synthesis by Self-Enhancing Generative Model

Qiu, Haonan; Wang, Chuan; Zhu, Hang; zhu, xiangyu; Gu, Jinjin; Han, Xiaoguang

Two-phase Hair Image Synthesis by Self-Enhancing Generative Model

Date

2019

Authors

Qiu, Haonan
Wang, Chuan
Zhu, Hang
zhu, xiangyu
Gu, Jinjin
Han, Xiaoguang

Publisher

The Eurographics Association and John Wiley & Sons Ltd.

Abstract

Generating plausible hair image given limited guidance, such as sparse sketches or low-resolution image, has been made possible with the rise of Generative Adversarial Networks (GANs). Traditional image-to-image translation networks can generate recognizable results, but finer textures are usually lost and blur artifacts commonly exist. In this paper, we propose a two-phase generative model for high-quality hair image synthesis. The two-phase pipeline first generates a coarse image by an existing image translation model, then applies a re-generating network with self-enhancing capability to the coarse image. The selfenhancing capability is achieved by a proposed differentiable layer, which extracts the structural texture and orientation maps from a hair image. Extensive experiments on two tasks, Sketch2Hair and Hair Super-Resolution, demonstrate that our approach is able to synthesize plausible hair image with finer details, and reaches the state-of-the-art.

        @article{10.1111:cgf.13847
,
journal = {Computer Graphics Forum},
title = {{Two-phase Hair Image Synthesis by Self-Enhancing Generative Model
}},
author = {Qiu, Haonan and 
Wang, Chuan and 
Zhu, Hang and 
zhu, xiangyu and 
Gu, Jinjin and 
Han, Xiaoguang
},
year = {2019
},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.13847
}
}