Motion Guided 3D Pose Estimation from Videos

    Cited by: 0|Bibtex|Views20|Links

    Abstract:

    We propose a new loss function, called motion loss, for the problem of monocular 3D Human pose estimation from 2D pose. In computing motion loss, a simple yet effective representation for keypoint motion, called pairwise motion encoding, is introduced. We design a new graph convolutional network architecture, U-shaped GCN (UGCN). It cap...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments