Transferring pose and augmenting background for deep humanimage parsing and its applications

查看全文 作　　者：Takazumi [1]Kikuchi;Yuki [1]Endo;Yoshihiro [1]Kanamori;Taisuke [1]Hashimoto;Jun [1]Mitani

机构地区：[1]University of Tsukuba,1-1-1 Tennohdai,Tsukuba City,Ibaraki,Japan

出　　处：《Computational Visual Media》索引2018年第4卷第1期,共12页

摘　　要：Parsing of human images is a fundamental task for determining semantic parts such as the face,arms, and legs, as well as a hat or a dress. Recent deep-learning-based methods have achieved significant improvements, but collecting training datasets with pixel-wise annotations is labor-intensive. In this paper,we propose two solutions to cope with limited datasets.Firstly, to handle various poses, we incorporate a pose estimation network into an end-to-end humanimage parsing network, in order to transfer common features across the domains. The pose estimation network can be trained using rich datasets and can feed valuable features to the human-image parsing network. Secondly, to handle complicated backgrounds,we increase the variation in image backgrounds automatically by replacing the original backgrounds of human images with others obtained from large-scale scenery image datasets. Individually, each solution is versatile and beneficial to human-image parsing, while their combination yields further improvement. We demonstrate the effectiveness of our approach through comparisons and various applications such as garment recoloring, garment texture transfer, and visualization for fashion analysis. 关键词：image segmentation semantic segmentation human-image parsing deep convolutional neural network

相关文献

参考文献（31）
引证文献（5）
耦合文献（0）

参考文献(31)

引证文献(5)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

Transferring pose and augmenting background for deep humanimage parsing and its applications

参考文献(31)

引证文献(5)

用户提示