Fast portrait automatic segmentation with coarse-to-fine CNNs

作     者：Zhang Xijin Li Ruilong Zhang Songhai 

作者机构：Department of Computer Science and Technology Tsinghua University 

出 版 物：《Computer Aided Drafting,Design and Manufacturing》 (计算机辅助绘图设计与制造（英文版）)

年 卷 期：2017年第27卷第2期

页      面：39-49页

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：Supported by the Natural Science Foundation of China(61521002,61373069) Research Grant of Beijing Higher Institution Engineering Research Center 

主　　题：convolutional neural network image segmentation machine learning 

摘      要：In this paper, we propose a coarse-to-fine convolutional network framework designed with problem specific knowledge for fast automatic portrait segmentation. We built up a dataset of 7 100 portrait images which are frames from personal live show videos. The proposed network includes a coarse network which can learn global information and a fine network which utilizes local information to refine the coarse output. Additionally, an auxiliary contour loss is introduced to help training the coarse network. The proposed framework shows higher accuracy than the widely-used fully convolutional network. With light-weight post-processing, the predicted foreground mask can be used in real-time portrait video editing tasks such as background replacement.