See Through the Inside and Outside: Human Body and Anatomical Skeleton Prediction Network

Zhiheng Peng, Kai Zhao, Xiaoran Chen, Yingfeng Chen, Changjie Fan, Bowei Tang, Siyu Xia, Weijian Shang

Abstract: In this work, it is the first time to use a monocular image with an arbitrary human pose to predict the human body and anatomical skeleton simultaneously. The framework, called STIO (See Through the Inside and Outside), considering the human anatomical con-straints, consists of a two-way reconstruction network that forms a strong collaboration between skeleton and skin.