2 code implementations • ICCV 2019 • Sun Yu, Ye Yun, Liu Wu, Gao Wenpeng, Fu YiLi, Mei Tao
Different from the existing methods try to obtain all the complex 3D pose, shape, and camera parameters from one coupling feature, we propose a skeleton-disentangling based framework, which divides this task into multi-level spatial and temporal granularity in a decoupling manner.
Ranked #112 on 3D Human Pose Estimation on 3DPW (PA-MPJPE metric, using extra training data)