KAD-Net: Kinematics-Aware Decoupled Learning for Robust 3D Hand Pose Estimation from a Single Depth Image
A Kinematics-Aware Decoupled Learning Network for robust 3D hand pose estimation and a task-decoupled hierarchical multitask framework, which separates 2D joint localization from depth estimation and incorporates a dedicated multitask learning strategy for depth regression.
Jun Lu, Zhen-Ming Chen, Lin Chen et al.
· 0 citations