Deep Automatic Portrait Matting

被引：148

作者：

Shen, Xiaoyong ^{[1
]}

Tao, Xin ^{[1
]}

Gao, Hongyun ^{[1
]}

Zhou, Chao ^{[1
]}

Jia, Jiaya ^{[1
]}

机构：

[1] Chinese Univ Hong Kong, Shatin, Hong Kong, Peoples R China

来源：

COMPUTER VISION - ECCV 2016, PT I | 2016年 / 9905卷

关键词：

Portrait; Matting; Automatic method; Neural network; IMAGE;

D O I：

10.1007/978-3-319-46448-0_6

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose an automatic image matting method for portrait images. This method does not need user interaction, which was however essential in most previous approaches. In order to accomplish this goal, a new end-to-end convolutional neural network (CNN) based framework is proposed taking the input of a portrait image. It outputs the matte result. Our method considers not only image semantic prediction but also pixel-level image matte optimization. A new portrait image dataset is constructed with our labeled matting ground truth. Our automatic method achieves comparable results with state-of-the-art methods that require specified foreground and background regions or pixels. Many applications are enabled given the automatic nature of our system.

引用

页码：92 / 107

页数：16