LEAP: Learning Articulated Occupancy of People
2021-06-18
LEAP (LEarning Articulated occupancy of People), a novel neural occupancy representation of the human body. It is effectively an implitic version of SMPL. Given a set of bone transformations (i.e. joint locations and rotations) and a query point in space, LEAP first maps the query point to a canonical space via learned linear blend skinning (LBS) functions and then efficiently queries the occupancy value via an occupancy network that models accurate identity- and pose- dependent deformations in the canonical space.
LEAP (LEarning Articulated occupancy of People), a novel neural occupancy representation of the human body. It is effectively an implitic version of SMPL. Given a set of bone transformations (i.e. joint locations and rotations) and a query point in space, LEAP first maps the query point to a canonical space via learned linear blend skinning (LBS) functions and then efficiently queries the occupancy value via an occupancy network that models accurate identity- and pose- dependent deformations in the canonical space.
| Author(s): | Marko Mihajlovic, Yan Zhang, Michael J. Black, Siyu Tang |
| Department(s): |
Perceiving Systems |
| Publication(s): |
{LEAP}: Learning Articulated Occupancy of People
|
| Authors: | Marko Mihajlovic, Yan Zhang, Michael J. Black, Siyu Tang |
| Release Date: | 2021-06-18 |
| Repository: | https://neuralbodies.github.io/LEAP/ |
